Open
[New operators] MACAQ W4A4 fused dense and grouped matmul for Ascend 950 #12568
Mocchibird Add on 20 days ago
[New operators] MACAQ W4A4 fused dense and grouped matmul for Ascend 950 #12568
Open
Mocchibird Add on 20 days ago
Total: 54 files changed+33941-12
Aexperimental/matmul/common/macaq/benchmark/README.md+131-0File content is under review, please try again later
@@ -0,0 +1,188 @@
1+[
2+ {
3+ "fixture": "accuracy-fixture-model_layers_0_mlp_down_proj.pt",
4+ "fixture_sha256": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
5+ "m": 1024,
6+ "k": 3072,
7+ "n": 1024,
8+ "tilelang_padded_n": 2048,
9+ "opsnn_padded_n": 7168,
10+ "experts": 4,
11+ "outputs": {
12+ "native_grouped_alg0": {
13+ "nmse": 0.030516970236956067,
14+ "nrmse": 0.17469107085640087,
15+ "max_abs_error": 0.25
16+ },
17+ "native_grouped_alg2": {
18+ "nmse": 0.031153790077059946,
19+ "nrmse": 0.1765043627706124,
20+ "max_abs_error": 0.19921875
21+ },
22+ "runs_standard": {
23+ "nmse": 0.018508736055048453,
24+ "nrmse": 0.13604681567404822,
25+ "max_abs_error": 0.248046875
26+ },
27+ "runs_prepared16": {
28+ "nmse": 0.018508736055048453,
29+ "nrmse": 0.13604681567404822,
30+ "max_abs_error": 0.248046875
31+ },
32+ "runs_prepared128": {
33+ "nmse": 0.018508736055048453,
34+ "nrmse": 0.13604681567404822,
35+ "max_abs_error": 0.248046875
36+ },
37+ "alternating16_standard": {
38+ "nmse": 0.018508736055048453,
39+ "nrmse": 0.13604681567404822,
40+ "max_abs_error": 0.248046875
41+ },
42+ "alternating16_prepared16": {
43+ "nmse": 0.018508736055048453,
44+ "nrmse": 0.13604681567404822,
45+ "max_abs_error": 0.248046875
46+ },
47+ "runs_opsnn": {
48+ "nmse": 0.018508736055048453,
49+ "nrmse": 0.13604681567404822,
50+ "max_abs_error": 0.248046875
51+ }
52+ },
53+ "cpu_max_abs": {
54+ "native_grouped_alg0": 0.0,
55+ "native_grouped_alg2": 0.0,
56+ "runs_standard": 0.0,
57+ "runs_prepared16": 0.0,
58+ "runs_prepared128": 0.0,
59+ "alternating16_standard": 0.0,
60+ "alternating16_prepared16": 0.0,
61+ "runs_opsnn": 0.0
62+ }
63+ },
64+ {
65+ "fixture": "accuracy-fixture-model_layers_14_mlp_down_proj.pt",
66+ "fixture_sha256": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
67+ "m": 1024,
68+ "k": 3072,
69+ "n": 1024,
70+ "tilelang_padded_n": 2048,
71+ "opsnn_padded_n": 7168,
72+ "experts": 4,
73+ "outputs": {
74+ "native_grouped_alg0": {
75+ "nmse": 0.03410957884917448,
76+ "nrmse": 0.18468778749331122,
77+ "max_abs_error": 1.5625
78+ },
79+ "native_grouped_alg2": {
80+ "nmse": 0.03799854210203062,
81+ "nrmse": 0.19493214743092177,
82+ "max_abs_error": 1.8125
83+ },
84+ "runs_standard": {
85+ "nmse": 0.021642116309140973,
86+ "nrmse": 0.1471125973842518,
87+ "max_abs_error": 0.7265625
88+ },
89+ "runs_prepared16": {
90+ "nmse": 0.021642116309140973,
91+ "nrmse": 0.1471125973842518,
92+ "max_abs_error": 0.7265625
93+ },
94+ "runs_prepared128": {
95+ "nmse": 0.021642116309140973,
96+ "nrmse": 0.1471125973842518,
97+ "max_abs_error": 0.7265625
98+ },
99+ "alternating16_standard": {
100+ "nmse": 0.021642116309140973,
101+ "nrmse": 0.1471125973842518,
102+ "max_abs_error": 0.7265625
103+ },
104+ "alternating16_prepared16": {
105+ "nmse": 0.021642116309140973,
106+ "nrmse": 0.1471125973842518,
107+ "max_abs_error": 0.7265625
108+ },
109+ "runs_opsnn": {
110+ "nmse": 0.021642116309140973,
111+ "nrmse": 0.1471125973842518,
112+ "max_abs_error": 0.7265625
113+ }
114+ },
115+ "cpu_max_abs": {
116+ "native_grouped_alg0": 0.0,
117+ "native_grouped_alg2": 0.0,
118+ "runs_standard": 0.0,
119+ "runs_prepared16": 0.0,
120+ "runs_prepared128": 0.0,
121+ "alternating16_standard": 0.0,
122+ "alternating16_prepared16": 0.0,
123+ "runs_opsnn": 0.0
124+ }
125+ },
126+ {
127+ "fixture": "accuracy-fixture-model_layers_27_mlp_down_proj.pt",
128+ "fixture_sha256": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
129+ "m": 1024,
130+ "k": 3072,
131+ "n": 1024,
132+ "tilelang_padded_n": 2048,
133+ "opsnn_padded_n": 7168,
134+ "experts": 4,
135+ "outputs": {
136+ "native_grouped_alg0": {
137+ "nmse": 0.021753115704479336,
138+ "nrmse": 0.14748937488673322,
139+ "max_abs_error": 720.0
140+ },
141+ "native_grouped_alg2": {
142+ "nmse": 0.019562300238837857,
143+ "nrmse": 0.13986529318897473,
144+ "max_abs_error": 192.0
145+ },
146+ "runs_standard": {
147+ "nmse": 0.0047220473550336605,
148+ "nrmse": 0.06871715473616222,
149+ "max_abs_error": 288.0
150+ },
151+ "runs_prepared16": {
152+ "nmse": 0.0047220473550336605,
153+ "nrmse": 0.06871715473616222,
154+ "max_abs_error": 288.0
155+ },
156+ "runs_prepared128": {
157+ "nmse": 0.0047220473550336605,
158+ "nrmse": 0.06871715473616222,
159+ "max_abs_error": 288.0
160+ },
161+ "alternating16_standard": {
162+ "nmse": 0.0047220473550336605,
163+ "nrmse": 0.06871715473616222,
164+ "max_abs_error": 288.0
165+ },
166+ "alternating16_prepared16": {
167+ "nmse": 0.0047220473550336605,
168+ "nrmse": 0.06871715473616222,
169+ "max_abs_error": 288.0
170+ },
171+ "runs_opsnn": {
172+ "nmse": 0.0047220473550336605,
173+ "nrmse": 0.06871715473616222,
174+ "max_abs_error": 288.0
175+ }
176+ },
177+ "cpu_max_abs": {
178+ "native_grouped_alg0": 0.0,
179+ "native_grouped_alg2": 0.0,
180+ "runs_standard": 0.0,
181+ "runs_prepared16": 0.0,
182+ "runs_prepared128": 0.0,
183+ "alternating16_standard": 0.0,
184+ "alternating16_prepared16": 0.0,
185+ "runs_opsnn": 0.0
186+ }
187+ }
188+]
@@ -0,0 +1,24 @@
1+{
2+ "checks": 24,
3+ "fixtures": 3,
4+ "source_sha256": {
5+ "src/cann_ops_tilelang/__init__.py": "a81e80bbf9fd868d5109d2ab725dec9afe16d0a346ccad7809e55fb6dddfd2a7",
6+ "src/cann_ops_tilelang/matmul/__init__.py": "13c8e8bdf2323d8787bcdf944464e1975343b35fe95a95e40d8d5612cec5a1eb",
7+ "src/cann_ops_tilelang/matmul/macaq_w4a4_matmul.py": "039334d011a6c5714be28066c1dc12a00868ac4a9fea1c640ed974a61bf830b8",
8+ "src/cann_ops_tilelang/matmul/macaq_w4a4_matmul_kernel.py": "fb33d479bb11db9ca3617c029d8c40dc7135af1baf0571346b6add11884bd777",
9+ "src/cann_ops_tilelang/matmul/macaq_w4a4_global_kernel.py": "128169df74198a73da97292edc8d9aefe9caee6cfe70c3c2b2b88fe024c0d65c",
10+ "src/cann_ops_tilelang/matmul/macaq_w4a4_dynamic_group_kernel.py": "c4a61194f87466de63e30b5f412146ce08f14eab7c5a1887cf83a2328b39212a",
11+ "tests/matmul/test_macaq_w4a4_matmul.py": "4af44fcb180beade6cbba3fe49c156603c69c7c8a4a652a52f134e01abf37293",
12+ "tests/test_macaq_contract.py": "fd971a2be888b2a2387a39e6a75a5f4765bb023635301a20bdc848a866eba978"
13+ },
14+ "fixture_sha256": {
15+ "accuracy-fixture-model_layers_0_mlp_down_proj.pt": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
16+ "accuracy-fixture-model_layers_14_mlp_down_proj.pt": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
17+ "accuracy-fixture-model_layers_27_mlp_down_proj.pt": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25"
18+ },
19+ "harness_sha256": "dc688dc4f2786a3b9005fe2ea5cd2660d4100d732adeaa29d3c644e0353d955b",
20+ "scope": "Grouped arithmetic check on three preselected real down-projection fixtures. Four replicated expert banks; Nzero-padding only, sliced original columns. No MoE-model evaluation or runtime claim. Alternating16 routes valid only for standard/prepared16; prepared128 andopsnn usecontiguous256-row runs.",
21+ "torch": "2.9.0+cpu",
22+ "torch_npu": "2.9.0.post2",
23+ "device": "Ascend950DT_9592"
24+}
@@ -0,0 +1,200 @@
1+[
2+ {
3+ "layer": "model.layers.0.self_attn.q_proj",
4+ "m": 1024,
5+ "k": 1024,
6+ "n": 2048,
7+ "plain_w4a4": {
8+ "nmse": 0.012961809523403645,
9+ "nrmse": 0.11384994301010275,
10+ "sqnr_db": 18.873343648873842,
11+ "cosine": 0.9924591183662415,
12+ "max_abs_error": 1.015625
13+ },
14+ "macaq_w4a4": {
15+ "nmse": 0.005795283708721399,
16+ "nrmse": 0.07612676079225622,
17+ "sqnr_db": 22.369252982480702,
18+ "cosine": 0.9948984980583191,
19+ "max_abs_error": 0.46875
20+ },
21+ "elapsed_cpu_seconds": 0.3079274800256826,
22+ "nmse_reduction_factor": 2.236613455851565
23+ },
24+ {
25+ "layer": "model.layers.0.mlp.up_proj",
26+ "m": 1024,
27+ "k": 1024,
28+ "n": 3072,
29+ "plain_w4a4": {
30+ "nmse": 0.03272208198904991,
31+ "nrmse": 0.18089245973519713,
32+ "sqnr_db": 14.8515907151692,
33+ "cosine": 0.9813424348831177,
34+ "max_abs_error": 0.640625
35+ },
36+ "macaq_w4a4": {
37+ "nmse": 0.018918711692094803,
38+ "nrmse": 0.1375453077792725,
39+ "sqnr_db": 17.231084410877195,
40+ "cosine": 0.9877645969390869,
41+ "max_abs_error": 0.3671875
42+ },
43+ "elapsed_cpu_seconds": 0.5210358299664222,
44+ "nmse_reduction_factor": 1.7296147074709562
45+ },
46+ {
47+ "layer": "model.layers.0.mlp.down_proj",
48+ "m": 1024,
49+ "k": 3072,
50+ "n": 1024,
51+ "plain_w4a4": {
52+ "nmse": 0.0305169690400362,
53+ "nrmse": 0.17469106743058216,
54+ "sqnr_db": 15.154586029109385,
55+ "cosine": 0.9849362373352051,
56+ "max_abs_error": 0.25
57+ },
58+ "macaq_w4a4": {
59+ "nmse": 0.018508734181523323,
60+ "nrmse": 0.13604680878845826,
61+ "sqnr_db": 17.32623281775322,
62+ "cosine": 0.9904028177261353,
63+ "max_abs_error": 0.248046875
64+ },
65+ "elapsed_cpu_seconds": 0.8360411199973896,
66+ "nmse_reduction_factor": 1.6487874719439386
67+ },
68+ {
69+ "layer": "model.layers.14.self_attn.q_proj",
70+ "m": 1024,
71+ "k": 1024,
72+ "n": 2048,
73+ "plain_w4a4": {
74+ "nmse": 0.014667452313005924,
75+ "nrmse": 0.12110925775103208,
76+ "sqnr_db": 18.336453150926808,
77+ "cosine": 0.9908798933029175,
78+ "max_abs_error": 2.640625
79+ },
80+ "macaq_w4a4": {
81+ "nmse": 0.007576686330139637,
82+ "nrmse": 0.08704416310206926,
83+ "sqnr_db": 21.20520691886017,
84+ "cosine": 0.9940814971923828,
85+ "max_abs_error": 2.1171875
86+ },
87+ "elapsed_cpu_seconds": 0.24619967996841297,
88+ "nmse_reduction_factor": 1.9358663766585684
89+ },
90+ {
91+ "layer": "model.layers.14.mlp.up_proj",
92+ "m": 1024,
93+ "k": 1024,
94+ "n": 3072,
95+ "plain_w4a4": {
96+ "nmse": 0.027274655178189278,
97+ "nrmse": 0.16515040168945783,
98+ "sqnr_db": 15.642407313044702,
99+ "cosine": 0.9838981628417969,
100+ "max_abs_error": 1.109375
101+ },
102+ "macaq_w4a4": {
103+ "nmse": 0.01696912758052349,
104+ "nrmse": 0.13026560398095688,
105+ "sqnr_db": 17.703404851251104,
106+ "cosine": 0.98872971534729,
107+ "max_abs_error": 0.671875
108+ },
109+ "elapsed_cpu_seconds": 0.4196922399569303,
110+ "nmse_reduction_factor": 1.6073103964103654
111+ },
112+ {
113+ "layer": "model.layers.14.mlp.down_proj",
114+ "m": 1024,
115+ "k": 3072,
116+ "n": 1024,
117+ "plain_w4a4": {
118+ "nmse": 0.034109581261873245,
119+ "nrmse": 0.1846877940251419,
120+ "sqnr_db": 14.671236120723465,
121+ "cosine": 0.9827119708061218,
122+ "max_abs_error": 1.5625
123+ },
124+ "macaq_w4a4": {
125+ "nmse": 0.021642116829752922,
126+ "nrmse": 0.1471125991536854,
127+ "sqnr_db": 16.647002628575503,
128+ "cosine": 0.988767147064209,
129+ "max_abs_error": 0.7265625
130+ },
131+ "elapsed_cpu_seconds": 0.7801028800313361,
132+ "nmse_reduction_factor": 1.5760741673374774
133+ },
134+ {
135+ "layer": "model.layers.27.self_attn.q_proj",
136+ "m": 1024,
137+ "k": 1024,
138+ "n": 2048,
139+ "plain_w4a4": {
140+ "nmse": 0.014878039248287678,
141+ "nrmse": 0.12197556824334814,
142+ "sqnr_db": 18.274542999566947,
143+ "cosine": 0.9907159805297852,
144+ "max_abs_error": 32.5
145+ },
146+ "macaq_w4a4": {
147+ "nmse": 0.007906630635261536,
148+ "nrmse": 0.08891923658726235,
149+ "sqnr_db": 21.020085491517307,
150+ "cosine": 0.9939277768135071,
151+ "max_abs_error": 17.75
152+ },
153+ "elapsed_cpu_seconds": 0.2413272900157608,
154+ "nmse_reduction_factor": 1.8817167431516852
155+ },
156+ {
157+ "layer": "model.layers.27.mlp.up_proj",
158+ "m": 1024,
159+ "k": 1024,
160+ "n": 3072,
161+ "plain_w4a4": {
162+ "nmse": 0.02178797498345375,
163+ "nrmse": 0.14760750314077448,
164+ "sqnr_db": 16.61783132047438,
165+ "cosine": 0.9861671328544617,
166+ "max_abs_error": 53.0
167+ },
168+ "macaq_w4a4": {
169+ "nmse": 0.008336487226188183,
170+ "nrmse": 0.09130436586597698,
171+ "sqnr_db": 20.790169109517755,
172+ "cosine": 0.9920082092285156,
173+ "max_abs_error": 39.0
174+ },
175+ "elapsed_cpu_seconds": 0.39534480997826904,
176+ "nmse_reduction_factor": 2.6135678484589
177+ },
178+ {
179+ "layer": "model.layers.27.mlp.down_proj",
180+ "m": 1024,
181+ "k": 3072,
182+ "n": 1024,
183+ "plain_w4a4": {
184+ "nmse": 0.021753111854195595,
185+ "nrmse": 0.14748936183398312,
186+ "sqnr_db": 16.62478607011158,
187+ "cosine": 0.9891892671585083,
188+ "max_abs_error": 720.0
189+ },
190+ "macaq_w4a4": {
191+ "nmse": 0.004722047131508589,
192+ "nrmse": 0.06871715310974828,
193+ "sqnr_db": 23.258696824728887,
194+ "cosine": 0.9965612888336182,
195+ "max_abs_error": 288.0
196+ },
197+ "elapsed_cpu_seconds": 0.8263739600079134,
198+ "nmse_reduction_factor": 4.606712141656655
199+ }
200+]
@@ -0,0 +1,40 @@
1+{
2+ "model": "Qwen/Qwen3-0.6B",
3+ "revision": "c1899de289a04d12100db370d81485cdf75e47ca",
4+ "torch": "2.9.0+cpu",
5+ "execution": "CPU-only method study; not model perplexity or NPU timing",
6+ "dataset": "Salesforce/wikitext wikitext-2-raw-v1",
7+ "calibration_tokens": 1024,
8+ "heldout_tokens": 1024,
9+ "token_sha256": {
10+ "train": "ea0c105aae5e1f26ceb3a387594b84f26c4e53dc1ddaccdc2f15d68751f917e9",
11+ "test": "5972d1f241a23f491babc9456f2ec33790d009894d23fbfcf903f6b9d2efdc32"
12+ },
13+ "selected_layers": [
14+ "model.layers.0.self_attn.q_proj",
15+ "model.layers.0.mlp.up_proj",
16+ "model.layers.0.mlp.down_proj",
17+ "model.layers.14.self_attn.q_proj",
18+ "model.layers.14.mlp.up_proj",
19+ "model.layers.14.mlp.down_proj",
20+ "model.layers.27.self_attn.q_proj",
21+ "model.layers.27.mlp.up_proj",
22+ "model.layers.27.mlp.down_proj"
23+ ],
24+ "method_source_sha256": "f53f40ddd4006c43dde6a7fbc7f43b2f210ce2320f73562ef96bc6681401bc59",
25+ "reference_source_sha256": "f65f8d3229339fba1a1762edd0bbd9825e534690f15099185fc0eea1452b67f6",
26+ "calibration": {
27+ "pre_alpha": 0.75,
28+ "hadamard_block": 32,
29+ "flip_iters": 8,
30+ "ridge": 1.0,
31+ "exp_screen": [
32+ 1,
33+ 0,
34+ -1
35+ ]
36+ },
37+ "baseline": "ordinary block32 MXFP4 W4A4 RTN; activation scale algorithm matches native baseline scale_alg=0",
38+ "reference": "BF16-input/weight matmul accumulated in FP32 and rounded to BF16; no linear bias",
39+ "selection": "q_proj, up_proj, down_proj at first/middle/last transformer layer; fixed before evaluating held-out test"
40+}
@@ -0,0 +1,461 @@
1+[
2+ {
3+ "fixture": "accuracy-fixture-model_layers_0_mlp_down_proj.pt",
4+ "fixture_sha256": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
5+ "m": 1024,
6+ "k": 3072,
7+ "n": 1024,
8+ "opsnn_padded_k": 3072,
9+ "opsnn_padded_n": 7168,
10+ "plain_native": {
11+ "nmse": 0.030516970236956067,
12+ "nrmse": 0.17469107085640087,
13+ "sqnr_db": 15.154585858772782,
14+ "cosine": 0.9852403571117876,
15+ "max_abs_error": 0.25
16+ },
17+ "native_scale_alg2": {
18+ "nmse": 0.031153790077059946,
19+ "nrmse": 0.1765043627706124,
20+ "sqnr_db": 15.064891108210311,
21+ "cosine": 0.9843569751092435,
22+ "max_abs_error": 0.19921875
23+ },
24+ "native_scale_alg2_error": null,
25+ "tilelang_planned_macaq": {
26+ "nmse": 0.018508736055048453,
27+ "nrmse": 0.13604681567404822,
28+ "sqnr_db": 17.326232378143693,
29+ "cosine": 0.9908084532765248,
30+ "max_abs_error": 0.248046875
31+ },
32+ "tilelang_macaq": {
33+ "nmse": 0.018508736055048453,
34+ "nrmse": 0.13604681567404822,
35+ "sqnr_db": 17.326232378143693,
36+ "cosine": 0.9908084532765248,
37+ "max_abs_error": 0.248046875
38+ },
39+ "opsnn_macaq": {
40+ "nmse": 0.018508736055048453,
41+ "nrmse": 0.13604681567404822,
42+ "sqnr_db": 17.326232378143693,
43+ "cosine": 0.9908084532765248,
44+ "max_abs_error": 0.248046875
45+ },
46+ "cpu_reference_agreement": {
47+ "plain_max_abs": 0.0,
48+ "tilelang_max_abs": 0.0,
49+ "tilelang_planned_max_abs": 0.0,
50+ "opsnn_max_abs": 0.0
51+ }
52+ },
53+ {
54+ "fixture": "accuracy-fixture-model_layers_0_mlp_up_proj.pt",
55+ "fixture_sha256": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a",
56+ "m": 1024,
57+ "k": 1024,
58+ "n": 3072,
59+ "opsnn_padded_k": 2048,
60+ "opsnn_padded_n": 3072,
61+ "plain_native": {
62+ "nmse": 0.03272208139022038,
63+ "nrmse": 0.18089245807998844,
64+ "sqnr_db": 14.85159079464714,
65+ "cosine": 0.9837271166985933,
66+ "max_abs_error": 0.640625
67+ },
68+ "native_scale_alg2": {
69+ "nmse": 0.04013932103835252,
70+ "nrmse": 0.20034799983616638,
71+ "sqnr_db": 13.964299779320108,
72+ "cosine": 0.9798668105571983,
73+ "max_abs_error": 0.546875
74+ },
75+ "native_scale_alg2_error": null,
76+ "tilelang_planned_macaq": {
77+ "nmse": 0.018918712122045826,
78+ "nrmse": 0.13754530934221576,
79+ "sqnr_db": 17.231084312178428,
80+ "cosine": 0.9905704452715268,
81+ "max_abs_error": 0.3671875
82+ },
83+ "tilelang_macaq": {
84+ "nmse": 0.018918712122045826,
85+ "nrmse": 0.13754530934221576,
86+ "sqnr_db": 17.231084312178428,
87+ "cosine": 0.9905704452715268,
88+ "max_abs_error": 0.3671875
89+ },
90+ "opsnn_macaq": {
91+ "nmse": 0.018918712122045826,
92+ "nrmse": 0.13754530934221576,
93+ "sqnr_db": 17.231084312178428,
94+ "cosine": 0.9905704452715268,
95+ "max_abs_error": 0.3671875
96+ },
97+ "cpu_reference_agreement": {
98+ "plain_max_abs": 0.0,
99+ "tilelang_max_abs": 0.0,
100+ "tilelang_planned_max_abs": 0.0,
101+ "opsnn_max_abs": 0.0
102+ }
103+ },
104+ {
105+ "fixture": "accuracy-fixture-model_layers_0_self_attn_q_proj.pt",
106+ "fixture_sha256": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
107+ "m": 1024,
108+ "k": 1024,
109+ "n": 2048,
110+ "opsnn_padded_k": 1536,
111+ "opsnn_padded_n": 2048,
112+ "plain_native": {
113+ "nmse": 0.012961810244357238,
114+ "nrmse": 0.11384994617634757,
115+ "sqnr_db": 18.873343407313314,
116+ "cosine": 0.9945141181596306,
117+ "max_abs_error": 1.015625
118+ },
119+ "native_scale_alg2": {
120+ "nmse": 0.011486990046041059,
121+ "nrmse": 0.10717737655886647,
122+ "sqnr_db": 19.39793755266881,
123+ "cosine": 0.9943654953511734,
124+ "max_abs_error": 1.20703125
125+ },
126+ "native_scale_alg2_error": null,
127+ "tilelang_planned_macaq": {
128+ "nmse": 0.005795284495877784,
129+ "nrmse": 0.07612676596229334,
130+ "sqnr_db": 22.36925239259129,
131+ "cosine": 0.9972342905702456,
132+ "max_abs_error": 0.46875
133+ },
134+ "tilelang_macaq": {
135+ "nmse": 0.005795284495877784,
136+ "nrmse": 0.07612676596229334,
137+ "sqnr_db": 22.36925239259129,
138+ "cosine": 0.9972342905702456,
139+ "max_abs_error": 0.46875
140+ },
141+ "opsnn_macaq": {
142+ "nmse": 0.005795284495877784,
143+ "nrmse": 0.07612676596229334,
144+ "sqnr_db": 22.36925239259129,
145+ "cosine": 0.9972342905702456,
146+ "max_abs_error": 0.46875
147+ },
148+ "cpu_reference_agreement": {
149+ "plain_max_abs": 0.0,
150+ "tilelang_max_abs": 0.0,
151+ "tilelang_planned_max_abs": 0.0,
152+ "opsnn_max_abs": 0.0
153+ }
154+ },
155+ {
156+ "fixture": "accuracy-fixture-model_layers_14_mlp_down_proj.pt",
157+ "fixture_sha256": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
158+ "m": 1024,
159+ "k": 3072,
160+ "n": 1024,
161+ "opsnn_padded_k": 3072,
162+ "opsnn_padded_n": 7168,
163+ "plain_native": {
164+ "nmse": 0.03410957884917448,
165+ "nrmse": 0.18468778749331122,
166+ "sqnr_db": 14.671236427916272,
167+ "cosine": 0.9830276128202399,
168+ "max_abs_error": 1.5625
169+ },
170+ "native_scale_alg2": {
171+ "nmse": 0.03799854210203062,
172+ "nrmse": 0.19493214743092177,
173+ "sqnr_db": 14.202330657302781,
174+ "cosine": 0.9809640218643827,
175+ "max_abs_error": 1.8125
176+ },
177+ "native_scale_alg2_error": null,
178+ "tilelang_planned_macaq": {
179+ "nmse": 0.021642116309140973,
180+ "nrmse": 0.1471125973842518,
181+ "sqnr_db": 16.647002733047213,
182+ "cosine": 0.989176496558601,
183+ "max_abs_error": 0.7265625
184+ },
185+ "tilelang_macaq": {
186+ "nmse": 0.021642116309140973,
187+ "nrmse": 0.1471125973842518,
188+ "sqnr_db": 16.647002733047213,
189+ "cosine": 0.989176496558601,
190+ "max_abs_error": 0.7265625
191+ },
192+ "opsnn_macaq": {
193+ "nmse": 0.021642116309140973,
194+ "nrmse": 0.1471125973842518,
195+ "sqnr_db": 16.647002733047213,
196+ "cosine": 0.989176496558601,
197+ "max_abs_error": 0.7265625
198+ },
199+ "cpu_reference_agreement": {
200+ "plain_max_abs": 0.0,
201+ "tilelang_max_abs": 0.0,
202+ "tilelang_planned_max_abs": 0.0,
203+ "opsnn_max_abs": 0.0
204+ }
205+ },
206+ {
207+ "fixture": "accuracy-fixture-model_layers_14_mlp_up_proj.pt",
208+ "fixture_sha256": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
209+ "m": 1024,
210+ "k": 1024,
211+ "n": 3072,
212+ "opsnn_padded_k": 2048,
213+ "opsnn_padded_n": 3072,
214+ "plain_native": {
215+ "nmse": 0.027274659838753348,
216+ "nrmse": 0.16515041579951698,
217+ "sqnr_db": 15.642406570942896,
218+ "cosine": 0.9865070511505231,
219+ "max_abs_error": 1.109375
220+ },
221+ "native_scale_alg2": {
222+ "nmse": 0.030852923399939662,
223+ "nrmse": 0.17565000256174113,
224+ "sqnr_db": 15.107036790761057,
225+ "cosine": 0.9845036092016929,
226+ "max_abs_error": 1.03125
227+ },
228+ "native_scale_alg2_error": null,
229+ "tilelang_planned_macaq": {
230+ "nmse": 0.01696913017803275,
231+ "nrmse": 0.13026561395100686,
232+ "sqnr_db": 17.7034041864651,
233+ "cosine": 0.9915783593889278,
234+ "max_abs_error": 0.671875
235+ },
236+ "tilelang_macaq": {
237+ "nmse": 0.01696913017803275,
238+ "nrmse": 0.13026561395100686,
239+ "sqnr_db": 17.7034041864651,
240+ "cosine": 0.9915783593889278,
241+ "max_abs_error": 0.671875
242+ },
243+ "opsnn_macaq": {
244+ "nmse": 0.01696913017803275,
245+ "nrmse": 0.13026561395100686,
246+ "sqnr_db": 17.7034041864651,
247+ "cosine": 0.9915783593889278,
248+ "max_abs_error": 0.671875
249+ },
250+ "cpu_reference_agreement": {
251+ "plain_max_abs": 0.0,
252+ "tilelang_max_abs": 0.0,
253+ "tilelang_planned_max_abs": 0.0,
254+ "opsnn_max_abs": 0.0
255+ }
256+ },
257+ {
258+ "fixture": "accuracy-fixture-model_layers_14_self_attn_q_proj.pt",
259+ "fixture_sha256": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
260+ "m": 1024,
261+ "k": 1024,
262+ "n": 2048,
263+ "opsnn_padded_k": 1536,
264+ "opsnn_padded_n": 2048,
265+ "plain_native": {
266+ "nmse": 0.01466745110141977,
267+ "nrmse": 0.12110925274899424,
268+ "sqnr_db": 18.33645350967023,
269+ "cosine": 0.9930062509087988,
270+ "max_abs_error": 2.640625
271+ },
272+ "native_scale_alg2": {
273+ "nmse": 0.01625560235156519,
274+ "nrmse": 0.12749746017691957,
275+ "sqnr_db": 17.88996933081782,
276+ "cosine": 0.9918593472312802,
277+ "max_abs_error": 3.3125
278+ },
279+ "native_scale_alg2_error": null,
280+ "tilelang_planned_macaq": {
281+ "nmse": 0.0075766859551332265,
282+ "nrmse": 0.08704416094795346,
283+ "sqnr_db": 21.205207133813268,
284+ "cosine": 0.9962798805014916,
285+ "max_abs_error": 2.1171875
286+ },
287+ "tilelang_macaq": {
288+ "nmse": 0.0075766859551332265,
289+ "nrmse": 0.08704416094795346,
290+ "sqnr_db": 21.205207133813268,
291+ "cosine": 0.9962798805014916,
292+ "max_abs_error": 2.1171875
293+ },
294+ "opsnn_macaq": {
295+ "nmse": 0.0075766859551332265,
296+ "nrmse": 0.08704416094795346,
297+ "sqnr_db": 21.205207133813268,
298+ "cosine": 0.9962798805014916,
299+ "max_abs_error": 2.1171875
300+ },
301+ "cpu_reference_agreement": {
302+ "plain_max_abs": 0.0,
303+ "tilelang_max_abs": 0.0,
304+ "tilelang_planned_max_abs": 0.0,
305+ "opsnn_max_abs": 0.0
306+ }
307+ },
308+ {
309+ "fixture": "accuracy-fixture-model_layers_27_mlp_down_proj.pt",
310+ "fixture_sha256": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
311+ "m": 1024,
312+ "k": 3072,
313+ "n": 1024,
314+ "opsnn_padded_k": 3072,
315+ "opsnn_padded_n": 7168,
316+ "plain_native": {
317+ "nmse": 0.021753115704479336,
318+ "nrmse": 0.14748937488673322,
319+ "sqnr_db": 16.62478530141382,
320+ "cosine": 0.9903826287274079,
321+ "max_abs_error": 720.0
322+ },
323+ "native_scale_alg2": {
324+ "nmse": 0.019562300238837857,
325+ "nrmse": 0.13986529318897473,
326+ "sqnr_db": 17.085800799012137,
327+ "cosine": 0.990239036351425,
328+ "max_abs_error": 192.0
329+ },
330+ "native_scale_alg2_error": null,
331+ "tilelang_planned_macaq": {
332+ "nmse": 0.0047220473550336605,
333+ "nrmse": 0.06871715473616222,
334+ "sqnr_db": 23.258696619149188,
335+ "cosine": 0.9980580611788563,
336+ "max_abs_error": 288.0
337+ },
338+ "tilelang_macaq": {
339+ "nmse": 0.0047220473550336605,
340+ "nrmse": 0.06871715473616222,
341+ "sqnr_db": 23.258696619149188,
342+ "cosine": 0.9980580611788563,
343+ "max_abs_error": 288.0
344+ },
345+ "opsnn_macaq": {
346+ "nmse": 0.0047220473550336605,
347+ "nrmse": 0.06871715473616222,
348+ "sqnr_db": 23.258696619149188,
349+ "cosine": 0.9980580611788563,
350+ "max_abs_error": 288.0
351+ },
352+ "cpu_reference_agreement": {
353+ "plain_max_abs": 0.0,
354+ "tilelang_max_abs": 0.0,
355+ "tilelang_planned_max_abs": 0.0,
356+ "opsnn_max_abs": 0.0
357+ }
358+ },
359+ {
360+ "fixture": "accuracy-fixture-model_layers_27_mlp_up_proj.pt",
361+ "fixture_sha256": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
362+ "m": 1024,
363+ "k": 1024,
364+ "n": 3072,
365+ "opsnn_padded_k": 2048,
366+ "opsnn_padded_n": 3072,
367+ "plain_native": {
368+ "nmse": 0.021787974624019088,
369+ "nrmse": 0.1476075019232393,
370+ "sqnr_db": 16.61783139211963,
371+ "cosine": 0.9896387374240014,
372+ "max_abs_error": 53.0
373+ },
374+ "native_scale_alg2": {
375+ "nmse": 0.025910815855607353,
376+ "nrmse": 0.16096836911520024,
377+ "sqnr_db": 15.865189121392245,
378+ "cosine": 0.9869727854323713,
379+ "max_abs_error": 33.734375
380+ },
381+ "native_scale_alg2_error": null,
382+ "tilelang_planned_macaq": {
383+ "nmse": 0.008336486324689736,
384+ "nrmse": 0.09130436092920062,
385+ "sqnr_db": 20.790169579159002,
386+ "cosine": 0.9959198014115227,
387+ "max_abs_error": 39.0
388+ },
389+ "tilelang_macaq": {
390+ "nmse": 0.008336486324689736,
391+ "nrmse": 0.09130436092920062,
392+ "sqnr_db": 20.790169579159002,
393+ "cosine": 0.9959198014115227,
394+ "max_abs_error": 39.0
395+ },
396+ "opsnn_macaq": {
397+ "nmse": 0.008336486324689736,
398+ "nrmse": 0.09130436092920062,
399+ "sqnr_db": 20.790169579159002,
400+ "cosine": 0.9959198014115227,
401+ "max_abs_error": 39.0
402+ },
403+ "cpu_reference_agreement": {
404+ "plain_max_abs": 0.0,
405+ "tilelang_max_abs": 0.0,
406+ "tilelang_planned_max_abs": 0.0,
407+ "opsnn_max_abs": 0.0
408+ }
409+ },
410+ {
411+ "fixture": "accuracy-fixture-model_layers_27_self_attn_q_proj.pt",
412+ "fixture_sha256": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
413+ "m": 1024,
414+ "k": 1024,
415+ "n": 2048,
416+ "opsnn_padded_k": 1536,
417+ "opsnn_padded_n": 2048,
418+ "plain_native": {
419+ "nmse": 0.014878039646034468,
420+ "nrmse": 0.12197556987378443,
421+ "sqnr_db": 18.27454288346345,
422+ "cosine": 0.9928836409767186,
423+ "max_abs_error": 32.5
424+ },
425+ "native_scale_alg2": {
426+ "nmse": 0.017160446816167834,
427+ "nrmse": 0.13099788859431222,
428+ "sqnr_db": 17.654714083713575,
429+ "cosine": 0.9913830249456285,
430+ "max_abs_error": 30.0
431+ },
432+ "native_scale_alg2_error": null,
433+ "tilelang_planned_macaq": {
434+ "nmse": 0.007906629422839765,
435+ "nrmse": 0.08891922976971722,
436+ "sqnr_db": 21.02008615747497,
437+ "cosine": 0.9961864477162093,
438+ "max_abs_error": 17.75
439+ },
440+ "tilelang_macaq": {
441+ "nmse": 0.007906629422839765,
442+ "nrmse": 0.08891922976971722,
443+ "sqnr_db": 21.02008615747497,
444+ "cosine": 0.9961864477162093,
445+ "max_abs_error": 17.75
446+ },
447+ "opsnn_macaq": {
448+ "nmse": 0.007906629422839765,
449+ "nrmse": 0.08891922976971722,
450+ "sqnr_db": 21.02008615747497,
451+ "cosine": 0.9961864477162093,
452+ "max_abs_error": 17.75
453+ },
454+ "cpu_reference_agreement": {
455+ "plain_max_abs": 0.0,
456+ "tilelang_max_abs": 0.0,
457+ "tilelang_planned_max_abs": 0.0,
458+ "opsnn_max_abs": 0.0
459+ }
460+ }
461+]
@@ -0,0 +1,37 @@
1+{
2+ "device": "Ascend950DT_9592",
3+ "torch": "2.9.0+cpu",
4+ "torch_npu": "2.9.0.post2",
5+ "opsnn_wheel_sha256": "b284336b70f82a80a4c2feba59bbc7f53cf178563f988dd89e527ef44ad50e06",
6+ "source_cpp_sha256": {
7+ "experimental/matmul/common/macaq/macaq_hadamard_mxfp4.hpp": "c62ab428e2d712d38b44e2e2de71605210e73b7fc4edac087a96a8aeb48c3574",
8+ "experimental/matmul/common/macaq/macaq_w4a4_kernel_impl.hpp": "52a5ed13b6798df7b36cdc08335663b2ffb70b52bda12180712b0dbb1ea1c26c",
9+ "experimental/matmul/macaq_w4a4_matmul/macaq_w4a4_matmul.cpp": "2ddea3d5dc3eed689a3aa59a43e219247b47344180a8ea23c24f94316a05ff44",
10+ "experimental/matmul/macaq_w4a4_grouped_matmul/macaq_w4a4_grouped_matmul.cpp": "63637c9de33517b69800b4dd0d748c17cbe5910facab4e5db39de7f931d38c93",
11+ "experimental/matmul/common/macaq/tests/test_macaq_raw_diagonal.py": "72f7a4536734be62e733656ce6cc45bd4b445529d995a224bc6cf309d24c7ed7"
12+ },
13+ "tilelang_base_commit": "b7d8b14c1e14f2412e4a37ccecde85e6284d0349",
14+ "model": "Qwen/Qwen3-0.6B",
15+ "checks": 36,
16+ "native_scale_alg2_checks": 9,
17+ "tilelang_source_sha256": {
18+ "__init__.py": "a81e80bbf9fd868d5109d2ab725dec9afe16d0a346ccad7809e55fb6dddfd2a7",
19+ "matmul/__init__.py": "13c8e8bdf2323d8787bcdf944464e1975343b35fe95a95e40d8d5612cec5a1eb",
20+ "matmul/macaq_w4a4_matmul.py": "c0604c1535ecc4b29e9e62ec345bea133f42c0e9d8537b63b6728d00b27b6648",
21+ "matmul/macaq_w4a4_matmul_kernel.py": "faca71b569e0d54d6fa499e84765f0bcdcacbcbbd68651e359f990ce785b720e"
22+ },
23+ "scope": "nine real projection fixtures, actual native and MACaQ NPU outputs vs CPU algorithm references; not whole-model NPU evaluation or model throughput",
24+ "padding": "ops-nn zero-pads K/N to supported pairs and slices original columns; zero padding preserves block32 transform boundaries; no latency claim for padded calls",
25+ "fixture_sha256": {
26+ "accuracy-fixture-model_layers_14_mlp_up_proj.pt": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
27+ "accuracy-fixture-model_layers_14_mlp_down_proj.pt": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
28+ "accuracy-fixture-model_layers_14_self_attn_q_proj.pt": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
29+ "accuracy-fixture-model_layers_27_self_attn_q_proj.pt": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
30+ "accuracy-fixture-model_layers_27_mlp_up_proj.pt": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
31+ "accuracy-fixture-model_layers_27_mlp_down_proj.pt": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
32+ "accuracy-fixture-model_layers_0_self_attn_q_proj.pt": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
33+ "accuracy-fixture-model_layers_0_mlp_down_proj.pt": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
34+ "accuracy-fixture-model_layers_0_mlp_up_proj.pt": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a"
35+ },
36+ "harness_sha256": "2729878cd01f4e40b0e178e90eddaef382db2da9629e8212039efd3905eb4c36"
37+}
@@ -0,0 +1,317 @@
1+[
2+ {
3+ "fixture": "accuracy-fixture-model_layers_0_mlp_down_proj.pt",
4+ "fixture_sha256": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
5+ "m": 1024,
6+ "k": 3072,
7+ "n": 1024,
8+ "opsnn_padded_k": 3072,
9+ "opsnn_padded_n": 7168,
10+ "plain_native": {
11+ "nmse": 0.030516970236956067,
12+ "nrmse": 0.17469107085640087,
13+ "sqnr_db": 15.154585858772782,
14+ "cosine": 0.9852403571117876,
15+ "max_abs_error": 0.25
16+ },
17+ "tilelang_macaq": {
18+ "nmse": 0.018508736055048453,
19+ "nrmse": 0.13604681567404822,
20+ "sqnr_db": 17.326232378143693,
21+ "cosine": 0.9908084532765248,
22+ "max_abs_error": 0.248046875
23+ },
24+ "opsnn_macaq": {
25+ "nmse": 0.018508736055048453,
26+ "nrmse": 0.13604681567404822,
27+ "sqnr_db": 17.326232378143693,
28+ "cosine": 0.9908084532765248,
29+ "max_abs_error": 0.248046875
30+ },
31+ "cpu_reference_agreement": {
32+ "plain_max_abs": 0.0,
33+ "tilelang_max_abs": 0.0,
34+ "opsnn_max_abs": 0.0
35+ }
36+ },
37+ {
38+ "fixture": "accuracy-fixture-model_layers_0_mlp_up_proj.pt",
39+ "fixture_sha256": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a",
40+ "m": 1024,
41+ "k": 1024,
42+ "n": 3072,
43+ "opsnn_padded_k": 2048,
44+ "opsnn_padded_n": 3072,
45+ "plain_native": {
46+ "nmse": 0.03272208139022038,
47+ "nrmse": 0.18089245807998844,
48+ "sqnr_db": 14.85159079464714,
49+ "cosine": 0.9837271166985933,
50+ "max_abs_error": 0.640625
51+ },
52+ "tilelang_macaq": {
53+ "nmse": 0.018918712122045826,
54+ "nrmse": 0.13754530934221576,
55+ "sqnr_db": 17.231084312178428,
56+ "cosine": 0.9905704452715268,
57+ "max_abs_error": 0.3671875
58+ },
59+ "opsnn_macaq": {
60+ "nmse": 0.018918712122045826,
61+ "nrmse": 0.13754530934221576,
62+ "sqnr_db": 17.231084312178428,
63+ "cosine": 0.9905704452715268,
64+ "max_abs_error": 0.3671875
65+ },
66+ "cpu_reference_agreement": {
67+ "plain_max_abs": 0.0,
68+ "tilelang_max_abs": 0.0,
69+ "opsnn_max_abs": 0.0
70+ }
71+ },
72+ {
73+ "fixture": "accuracy-fixture-model_layers_0_self_attn_q_proj.pt",
74+ "fixture_sha256": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
75+ "m": 1024,
76+ "k": 1024,
77+ "n": 2048,
78+ "opsnn_padded_k": 1536,
79+ "opsnn_padded_n": 2048,
80+ "plain_native": {
81+ "nmse": 0.012961810244357238,
82+ "nrmse": 0.11384994617634757,
83+ "sqnr_db": 18.873343407313314,
84+ "cosine": 0.9945141181596306,
85+ "max_abs_error": 1.015625
86+ },
87+ "tilelang_macaq": {
88+ "nmse": 0.005795284495877784,
89+ "nrmse": 0.07612676596229334,
90+ "sqnr_db": 22.36925239259129,
91+ "cosine": 0.9972342905702456,
92+ "max_abs_error": 0.46875
93+ },
94+ "opsnn_macaq": {
95+ "nmse": 0.005795284495877784,
96+ "nrmse": 0.07612676596229334,
97+ "sqnr_db": 22.36925239259129,
98+ "cosine": 0.9972342905702456,
99+ "max_abs_error": 0.46875
100+ },
101+ "cpu_reference_agreement": {
102+ "plain_max_abs": 0.0,
103+ "tilelang_max_abs": 0.0,
104+ "opsnn_max_abs": 0.0
105+ }
106+ },
107+ {
108+ "fixture": "accuracy-fixture-model_layers_14_mlp_down_proj.pt",
109+ "fixture_sha256": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
110+ "m": 1024,
111+ "k": 3072,
112+ "n": 1024,
113+ "opsnn_padded_k": 3072,
114+ "opsnn_padded_n": 7168,
115+ "plain_native": {
116+ "nmse": 0.03410957884917448,
117+ "nrmse": 0.18468778749331122,
118+ "sqnr_db": 14.671236427916272,
119+ "cosine": 0.9830276128202399,
120+ "max_abs_error": 1.5625
121+ },
122+ "tilelang_macaq": {
123+ "nmse": 0.021642116309140973,
124+ "nrmse": 0.1471125973842518,
125+ "sqnr_db": 16.647002733047213,
126+ "cosine": 0.989176496558601,
127+ "max_abs_error": 0.7265625
128+ },
129+ "opsnn_macaq": {
130+ "nmse": 0.021642116309140973,
131+ "nrmse": 0.1471125973842518,
132+ "sqnr_db": 16.647002733047213,
133+ "cosine": 0.989176496558601,
134+ "max_abs_error": 0.7265625
135+ },
136+ "cpu_reference_agreement": {
137+ "plain_max_abs": 0.0,
138+ "tilelang_max_abs": 0.0,
139+ "opsnn_max_abs": 0.0
140+ }
141+ },
142+ {
143+ "fixture": "accuracy-fixture-model_layers_14_mlp_up_proj.pt",
144+ "fixture_sha256": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
145+ "m": 1024,
146+ "k": 1024,
147+ "n": 3072,
148+ "opsnn_padded_k": 2048,
149+ "opsnn_padded_n": 3072,
150+ "plain_native": {
151+ "nmse": 0.027274659838753348,
152+ "nrmse": 0.16515041579951698,
153+ "sqnr_db": 15.642406570942896,
154+ "cosine": 0.9865070511505231,
155+ "max_abs_error": 1.109375
156+ },
157+ "tilelang_macaq": {
158+ "nmse": 0.01696913017803275,
159+ "nrmse": 0.13026561395100686,
160+ "sqnr_db": 17.7034041864651,
161+ "cosine": 0.9915783593889278,
162+ "max_abs_error": 0.671875
163+ },
164+ "opsnn_macaq": {
165+ "nmse": 0.01696913017803275,
166+ "nrmse": 0.13026561395100686,
167+ "sqnr_db": 17.7034041864651,
168+ "cosine": 0.9915783593889278,
169+ "max_abs_error": 0.671875
170+ },
171+ "cpu_reference_agreement": {
172+ "plain_max_abs": 0.0,
173+ "tilelang_max_abs": 0.0,
174+ "opsnn_max_abs": 0.0
175+ }
176+ },
177+ {
178+ "fixture": "accuracy-fixture-model_layers_14_self_attn_q_proj.pt",
179+ "fixture_sha256": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
180+ "m": 1024,
181+ "k": 1024,
182+ "n": 2048,
183+ "opsnn_padded_k": 1536,
184+ "opsnn_padded_n": 2048,
185+ "plain_native": {
186+ "nmse": 0.01466745110141977,
187+ "nrmse": 0.12110925274899424,
188+ "sqnr_db": 18.33645350967023,
189+ "cosine": 0.9930062509087988,
190+ "max_abs_error": 2.640625
191+ },
192+ "tilelang_macaq": {
193+ "nmse": 0.0075766859551332265,
194+ "nrmse": 0.08704416094795346,
195+ "sqnr_db": 21.205207133813268,
196+ "cosine": 0.9962798805014916,
197+ "max_abs_error": 2.1171875
198+ },
199+ "opsnn_macaq": {
200+ "nmse": 0.0075766859551332265,
201+ "nrmse": 0.08704416094795346,
202+ "sqnr_db": 21.205207133813268,
203+ "cosine": 0.9962798805014916,
204+ "max_abs_error": 2.1171875
205+ },
206+ "cpu_reference_agreement": {
207+ "plain_max_abs": 0.0,
208+ "tilelang_max_abs": 0.0,
209+ "opsnn_max_abs": 0.0
210+ }
211+ },
212+ {
213+ "fixture": "accuracy-fixture-model_layers_27_mlp_down_proj.pt",
214+ "fixture_sha256": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
215+ "m": 1024,
216+ "k": 3072,
217+ "n": 1024,
218+ "opsnn_padded_k": 3072,
219+ "opsnn_padded_n": 7168,
220+ "plain_native": {
221+ "nmse": 0.021753115704479336,
222+ "nrmse": 0.14748937488673322,
223+ "sqnr_db": 16.62478530141382,
224+ "cosine": 0.9903826287274079,
225+ "max_abs_error": 720.0
226+ },
227+ "tilelang_macaq": {
228+ "nmse": 0.0047220473550336605,
229+ "nrmse": 0.06871715473616222,
230+ "sqnr_db": 23.258696619149188,
231+ "cosine": 0.9980580611788563,
232+ "max_abs_error": 288.0
233+ },
234+ "opsnn_macaq": {
235+ "nmse": 0.0047220473550336605,
236+ "nrmse": 0.06871715473616222,
237+ "sqnr_db": 23.258696619149188,
238+ "cosine": 0.9980580611788563,
239+ "max_abs_error": 288.0
240+ },
241+ "cpu_reference_agreement": {
242+ "plain_max_abs": 0.0,
243+ "tilelang_max_abs": 0.0,
244+ "opsnn_max_abs": 0.0
245+ }
246+ },
247+ {
248+ "fixture": "accuracy-fixture-model_layers_27_mlp_up_proj.pt",
249+ "fixture_sha256": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
250+ "m": 1024,
251+ "k": 1024,
252+ "n": 3072,
253+ "opsnn_padded_k": 2048,
254+ "opsnn_padded_n": 3072,
255+ "plain_native": {
256+ "nmse": 0.021787974624019088,
257+ "nrmse": 0.1476075019232393,
258+ "sqnr_db": 16.61783139211963,
259+ "cosine": 0.9896387374240014,
260+ "max_abs_error": 53.0
261+ },
262+ "tilelang_macaq": {
263+ "nmse": 0.008336486324689736,
264+ "nrmse": 0.09130436092920062,
265+ "sqnr_db": 20.790169579159002,
266+ "cosine": 0.9959198014115227,
267+ "max_abs_error": 39.0
268+ },
269+ "opsnn_macaq": {
270+ "nmse": 0.008336486324689736,
271+ "nrmse": 0.09130436092920062,
272+ "sqnr_db": 20.790169579159002,
273+ "cosine": 0.9959198014115227,
274+ "max_abs_error": 39.0
275+ },
276+ "cpu_reference_agreement": {
277+ "plain_max_abs": 0.0,
278+ "tilelang_max_abs": 0.0,
279+ "opsnn_max_abs": 0.0
280+ }
281+ },
282+ {
283+ "fixture": "accuracy-fixture-model_layers_27_self_attn_q_proj.pt",
284+ "fixture_sha256": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
285+ "m": 1024,
286+ "k": 1024,
287+ "n": 2048,
288+ "opsnn_padded_k": 1536,
289+ "opsnn_padded_n": 2048,
290+ "plain_native": {
291+ "nmse": 0.014878039646034468,
292+ "nrmse": 0.12197556987378443,
293+ "sqnr_db": 18.27454288346345,
294+ "cosine": 0.9928836409767186,
295+ "max_abs_error": 32.5
296+ },
297+ "tilelang_macaq": {
298+ "nmse": 0.007906629422839765,
299+ "nrmse": 0.08891922976971722,
300+ "sqnr_db": 21.02008615747497,
301+ "cosine": 0.9961864477162093,
302+ "max_abs_error": 17.75
303+ },
304+ "opsnn_macaq": {
305+ "nmse": 0.007906629422839765,
306+ "nrmse": 0.08891922976971722,
307+ "sqnr_db": 21.02008615747497,
308+ "cosine": 0.9961864477162093,
309+ "max_abs_error": 17.75
310+ },
311+ "cpu_reference_agreement": {
312+ "plain_max_abs": 0.0,
313+ "tilelang_max_abs": 0.0,
314+ "opsnn_max_abs": 0.0
315+ }
316+ }
317+]
@@ -0,0 +1,30 @@
1+{
2+ "device": "Ascend950DT_9592",
3+ "torch": "2.9.0+cpu",
4+ "torch_npu": "2.9.0.post2",
5+ "opsnn_wheel_sha256": "b284336b70f82a80a4c2feba59bbc7f53cf178563f988dd89e527ef44ad50e06",
6+ "source_cpp_sha256": {
7+ "experimental/matmul/common/macaq/macaq_hadamard_mxfp4.hpp": "c62ab428e2d712d38b44e2e2de71605210e73b7fc4edac087a96a8aeb48c3574",
8+ "experimental/matmul/common/macaq/macaq_w4a4_kernel_impl.hpp": "52a5ed13b6798df7b36cdc08335663b2ffb70b52bda12180712b0dbb1ea1c26c",
9+ "experimental/matmul/macaq_w4a4_matmul/macaq_w4a4_matmul.cpp": "2ddea3d5dc3eed689a3aa59a43e219247b47344180a8ea23c24f94316a05ff44",
10+ "experimental/matmul/macaq_w4a4_grouped_matmul/macaq_w4a4_grouped_matmul.cpp": "63637c9de33517b69800b4dd0d748c17cbe5910facab4e5db39de7f931d38c93",
11+ "experimental/matmul/common/macaq/tests/test_macaq_raw_diagonal.py": "72f7a4536734be62e733656ce6cc45bd4b445529d995a224bc6cf309d24c7ed7"
12+ },
13+ "tilelang_base_commit": "b7d8b14c1e14f2412e4a37ccecde85e6284d0349",
14+ "model": "Qwen/Qwen3-0.6B",
15+ "checks": 27,
16+ "scope": "nine real projection fixtures, actual native and MACaQ NPU outputs vs CPU algorithm references; not whole-model NPU evaluation or model throughput",
17+ "padding": "ops-nn zero-pads K/N to supported pairs and slices original columns; zero padding preserves block32 transform boundaries; no latency claim for padded calls",
18+ "fixture_sha256": {
19+ "accuracy-fixture-model_layers_14_mlp_up_proj.pt": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
20+ "accuracy-fixture-model_layers_14_mlp_down_proj.pt": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
21+ "accuracy-fixture-model_layers_14_self_attn_q_proj.pt": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
22+ "accuracy-fixture-model_layers_27_self_attn_q_proj.pt": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
23+ "accuracy-fixture-model_layers_27_mlp_up_proj.pt": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
24+ "accuracy-fixture-model_layers_27_mlp_down_proj.pt": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
25+ "accuracy-fixture-model_layers_0_self_attn_q_proj.pt": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
26+ "accuracy-fixture-model_layers_0_mlp_down_proj.pt": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
27+ "accuracy-fixture-model_layers_0_mlp_up_proj.pt": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a"
28+ },
29+ "harness_sha256": "506df5b86b8374788fc9e12aab2b0c884da8b383b2c5a8c0a1ed0a604963ddd4"
30+}
@@ -0,0 +1,461 @@
1+[
2+ {
3+ "fixture": "accuracy-fixture-model_layers_0_mlp_down_proj.pt",
4+ "fixture_sha256": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
5+ "m": 1024,
6+ "k": 3072,
7+ "n": 1024,
8+ "opsnn_padded_k": 3072,
9+ "opsnn_padded_n": 7168,
10+ "plain_native": {
11+ "nmse": 0.030516970236956067,
12+ "nrmse": 0.17469107085640087,
13+ "sqnr_db": 15.154585858772782,
14+ "cosine": 0.9852403571117876,
15+ "max_abs_error": 0.25
16+ },
17+ "native_scale_alg2": {
18+ "nmse": 0.031153790077059946,
19+ "nrmse": 0.1765043627706124,
20+ "sqnr_db": 15.064891108210311,
21+ "cosine": 0.9843569751092435,
22+ "max_abs_error": 0.19921875
23+ },
24+ "native_scale_alg2_error": null,
25+ "tilelang_planned_macaq": {
26+ "nmse": 0.018508736055048453,
27+ "nrmse": 0.13604681567404822,
28+ "sqnr_db": 17.326232378143693,
29+ "cosine": 0.9908084532765248,
30+ "max_abs_error": 0.248046875
31+ },
32+ "tilelang_macaq": {
33+ "nmse": 0.018508736055048453,
34+ "nrmse": 0.13604681567404822,
35+ "sqnr_db": 17.326232378143693,
36+ "cosine": 0.9908084532765248,
37+ "max_abs_error": 0.248046875
38+ },
39+ "opsnn_macaq": {
40+ "nmse": 0.018508736055048453,
41+ "nrmse": 0.13604681567404822,
42+ "sqnr_db": 17.326232378143693,
43+ "cosine": 0.9908084532765248,
44+ "max_abs_error": 0.248046875
45+ },
46+ "cpu_reference_agreement": {
47+ "plain_max_abs": 0.0,
48+ "tilelang_max_abs": 0.0,
49+ "tilelang_planned_max_abs": 0.0,
50+ "opsnn_max_abs": 0.0
51+ }
52+ },
53+ {
54+ "fixture": "accuracy-fixture-model_layers_0_mlp_up_proj.pt",
55+ "fixture_sha256": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a",
56+ "m": 1024,
57+ "k": 1024,
58+ "n": 3072,
59+ "opsnn_padded_k": 2048,
60+ "opsnn_padded_n": 3072,
61+ "plain_native": {
62+ "nmse": 0.03272208139022038,
63+ "nrmse": 0.18089245807998844,
64+ "sqnr_db": 14.85159079464714,
65+ "cosine": 0.9837271166985933,
66+ "max_abs_error": 0.640625
67+ },
68+ "native_scale_alg2": {
69+ "nmse": 0.04013932103835252,
70+ "nrmse": 0.20034799983616638,
71+ "sqnr_db": 13.964299779320108,
72+ "cosine": 0.9798668105571983,
73+ "max_abs_error": 0.546875
74+ },
75+ "native_scale_alg2_error": null,
76+ "tilelang_planned_macaq": {
77+ "nmse": 0.018918712122045826,
78+ "nrmse": 0.13754530934221576,
79+ "sqnr_db": 17.231084312178428,
80+ "cosine": 0.9905704452715268,
81+ "max_abs_error": 0.3671875
82+ },
83+ "tilelang_macaq": {
84+ "nmse": 0.018918712122045826,
85+ "nrmse": 0.13754530934221576,
86+ "sqnr_db": 17.231084312178428,
87+ "cosine": 0.9905704452715268,
88+ "max_abs_error": 0.3671875
89+ },
90+ "opsnn_macaq": {
91+ "nmse": 0.018918712122045826,
92+ "nrmse": 0.13754530934221576,
93+ "sqnr_db": 17.231084312178428,
94+ "cosine": 0.9905704452715268,
95+ "max_abs_error": 0.3671875
96+ },
97+ "cpu_reference_agreement": {
98+ "plain_max_abs": 0.0,
99+ "tilelang_max_abs": 0.0,
100+ "tilelang_planned_max_abs": 0.0,
101+ "opsnn_max_abs": 0.0
102+ }
103+ },
104+ {
105+ "fixture": "accuracy-fixture-model_layers_0_self_attn_q_proj.pt",
106+ "fixture_sha256": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
107+ "m": 1024,
108+ "k": 1024,
109+ "n": 2048,
110+ "opsnn_padded_k": 1536,
111+ "opsnn_padded_n": 2048,
112+ "plain_native": {
113+ "nmse": 0.012961810244357238,
114+ "nrmse": 0.11384994617634757,
115+ "sqnr_db": 18.873343407313314,
116+ "cosine": 0.9945141181596306,
117+ "max_abs_error": 1.015625
118+ },
119+ "native_scale_alg2": {
120+ "nmse": 0.011486990046041059,
121+ "nrmse": 0.10717737655886647,
122+ "sqnr_db": 19.39793755266881,
123+ "cosine": 0.9943654953511734,
124+ "max_abs_error": 1.20703125
125+ },
126+ "native_scale_alg2_error": null,
127+ "tilelang_planned_macaq": {
128+ "nmse": 0.005795284495877784,
129+ "nrmse": 0.07612676596229334,
130+ "sqnr_db": 22.36925239259129,
131+ "cosine": 0.9972342905702456,
132+ "max_abs_error": 0.46875
133+ },
134+ "tilelang_macaq": {
135+ "nmse": 0.005795284495877784,
136+ "nrmse": 0.07612676596229334,
137+ "sqnr_db": 22.36925239259129,
138+ "cosine": 0.9972342905702456,
139+ "max_abs_error": 0.46875
140+ },
141+ "opsnn_macaq": {
142+ "nmse": 0.005795284495877784,
143+ "nrmse": 0.07612676596229334,
144+ "sqnr_db": 22.36925239259129,
145+ "cosine": 0.9972342905702456,
146+ "max_abs_error": 0.46875
147+ },
148+ "cpu_reference_agreement": {
149+ "plain_max_abs": 0.0,
150+ "tilelang_max_abs": 0.0,
151+ "tilelang_planned_max_abs": 0.0,
152+ "opsnn_max_abs": 0.0
153+ }
154+ },
155+ {
156+ "fixture": "accuracy-fixture-model_layers_14_mlp_down_proj.pt",
157+ "fixture_sha256": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
158+ "m": 1024,
159+ "k": 3072,
160+ "n": 1024,
161+ "opsnn_padded_k": 3072,
162+ "opsnn_padded_n": 7168,
163+ "plain_native": {
164+ "nmse": 0.03410957884917448,
165+ "nrmse": 0.18468778749331122,
166+ "sqnr_db": 14.671236427916272,
167+ "cosine": 0.9830276128202399,
168+ "max_abs_error": 1.5625
169+ },
170+ "native_scale_alg2": {
171+ "nmse": 0.03799854210203062,
172+ "nrmse": 0.19493214743092177,
173+ "sqnr_db": 14.202330657302781,
174+ "cosine": 0.9809640218643827,
175+ "max_abs_error": 1.8125
176+ },
177+ "native_scale_alg2_error": null,
178+ "tilelang_planned_macaq": {
179+ "nmse": 0.021642116309140973,
180+ "nrmse": 0.1471125973842518,
181+ "sqnr_db": 16.647002733047213,
182+ "cosine": 0.989176496558601,
183+ "max_abs_error": 0.7265625
184+ },
185+ "tilelang_macaq": {
186+ "nmse": 0.021642116309140973,
187+ "nrmse": 0.1471125973842518,
188+ "sqnr_db": 16.647002733047213,
189+ "cosine": 0.989176496558601,
190+ "max_abs_error": 0.7265625
191+ },
192+ "opsnn_macaq": {
193+ "nmse": 0.021642116309140973,
194+ "nrmse": 0.1471125973842518,
195+ "sqnr_db": 16.647002733047213,
196+ "cosine": 0.989176496558601,
197+ "max_abs_error": 0.7265625
198+ },
199+ "cpu_reference_agreement": {
200+ "plain_max_abs": 0.0,
201+ "tilelang_max_abs": 0.0,
202+ "tilelang_planned_max_abs": 0.0,
203+ "opsnn_max_abs": 0.0
204+ }
205+ },
206+ {
207+ "fixture": "accuracy-fixture-model_layers_14_mlp_up_proj.pt",
208+ "fixture_sha256": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
209+ "m": 1024,
210+ "k": 1024,
211+ "n": 3072,
212+ "opsnn_padded_k": 2048,
213+ "opsnn_padded_n": 3072,
214+ "plain_native": {
215+ "nmse": 0.027274659838753348,
216+ "nrmse": 0.16515041579951698,
217+ "sqnr_db": 15.642406570942896,
218+ "cosine": 0.9865070511505231,
219+ "max_abs_error": 1.109375
220+ },
221+ "native_scale_alg2": {
222+ "nmse": 0.030852923399939662,
223+ "nrmse": 0.17565000256174113,
224+ "sqnr_db": 15.107036790761057,
225+ "cosine": 0.9845036092016929,
226+ "max_abs_error": 1.03125
227+ },
228+ "native_scale_alg2_error": null,
229+ "tilelang_planned_macaq": {
230+ "nmse": 0.01696913017803275,
231+ "nrmse": 0.13026561395100686,
232+ "sqnr_db": 17.7034041864651,
233+ "cosine": 0.9915783593889278,
234+ "max_abs_error": 0.671875
235+ },
236+ "tilelang_macaq": {
237+ "nmse": 0.01696913017803275,
238+ "nrmse": 0.13026561395100686,
239+ "sqnr_db": 17.7034041864651,
240+ "cosine": 0.9915783593889278,
241+ "max_abs_error": 0.671875
242+ },
243+ "opsnn_macaq": {
244+ "nmse": 0.01696913017803275,
245+ "nrmse": 0.13026561395100686,
246+ "sqnr_db": 17.7034041864651,
247+ "cosine": 0.9915783593889278,
248+ "max_abs_error": 0.671875
249+ },
250+ "cpu_reference_agreement": {
251+ "plain_max_abs": 0.0,
252+ "tilelang_max_abs": 0.0,
253+ "tilelang_planned_max_abs": 0.0,
254+ "opsnn_max_abs": 0.0
255+ }
256+ },
257+ {
258+ "fixture": "accuracy-fixture-model_layers_14_self_attn_q_proj.pt",
259+ "fixture_sha256": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
260+ "m": 1024,
261+ "k": 1024,
262+ "n": 2048,
263+ "opsnn_padded_k": 1536,
264+ "opsnn_padded_n": 2048,
265+ "plain_native": {
266+ "nmse": 0.01466745110141977,
267+ "nrmse": 0.12110925274899424,
268+ "sqnr_db": 18.33645350967023,
269+ "cosine": 0.9930062509087988,
270+ "max_abs_error": 2.640625
271+ },
272+ "native_scale_alg2": {
273+ "nmse": 0.01625560235156519,
274+ "nrmse": 0.12749746017691957,
275+ "sqnr_db": 17.88996933081782,
276+ "cosine": 0.9918593472312802,
277+ "max_abs_error": 3.3125
278+ },
279+ "native_scale_alg2_error": null,
280+ "tilelang_planned_macaq": {
281+ "nmse": 0.0075766859551332265,
282+ "nrmse": 0.08704416094795346,
283+ "sqnr_db": 21.205207133813268,
284+ "cosine": 0.9962798805014916,
285+ "max_abs_error": 2.1171875
286+ },
287+ "tilelang_macaq": {
288+ "nmse": 0.0075766859551332265,
289+ "nrmse": 0.08704416094795346,
290+ "sqnr_db": 21.205207133813268,
291+ "cosine": 0.9962798805014916,
292+ "max_abs_error": 2.1171875
293+ },
294+ "opsnn_macaq": {
295+ "nmse": 0.0075766859551332265,
296+ "nrmse": 0.08704416094795346,
297+ "sqnr_db": 21.205207133813268,
298+ "cosine": 0.9962798805014916,
299+ "max_abs_error": 2.1171875
300+ },
301+ "cpu_reference_agreement": {
302+ "plain_max_abs": 0.0,
303+ "tilelang_max_abs": 0.0,
304+ "tilelang_planned_max_abs": 0.0,
305+ "opsnn_max_abs": 0.0
306+ }
307+ },
308+ {
309+ "fixture": "accuracy-fixture-model_layers_27_mlp_down_proj.pt",
310+ "fixture_sha256": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
311+ "m": 1024,
312+ "k": 3072,
313+ "n": 1024,
314+ "opsnn_padded_k": 3072,
315+ "opsnn_padded_n": 7168,
316+ "plain_native": {
317+ "nmse": 0.021753115704479336,
318+ "nrmse": 0.14748937488673322,
319+ "sqnr_db": 16.62478530141382,
320+ "cosine": 0.9903826287274079,
321+ "max_abs_error": 720.0
322+ },
323+ "native_scale_alg2": {
324+ "nmse": 0.019562300238837857,
325+ "nrmse": 0.13986529318897473,
326+ "sqnr_db": 17.085800799012137,
327+ "cosine": 0.990239036351425,
328+ "max_abs_error": 192.0
329+ },
330+ "native_scale_alg2_error": null,
331+ "tilelang_planned_macaq": {
332+ "nmse": 0.0047220473550336605,
333+ "nrmse": 0.06871715473616222,
334+ "sqnr_db": 23.258696619149188,
335+ "cosine": 0.9980580611788563,
336+ "max_abs_error": 288.0
337+ },
338+ "tilelang_macaq": {
339+ "nmse": 0.0047220473550336605,
340+ "nrmse": 0.06871715473616222,
341+ "sqnr_db": 23.258696619149188,
342+ "cosine": 0.9980580611788563,
343+ "max_abs_error": 288.0
344+ },
345+ "opsnn_macaq": {
346+ "nmse": 0.0047220473550336605,
347+ "nrmse": 0.06871715473616222,
348+ "sqnr_db": 23.258696619149188,
349+ "cosine": 0.9980580611788563,
350+ "max_abs_error": 288.0
351+ },
352+ "cpu_reference_agreement": {
353+ "plain_max_abs": 0.0,
354+ "tilelang_max_abs": 0.0,
355+ "tilelang_planned_max_abs": 0.0,
356+ "opsnn_max_abs": 0.0
357+ }
358+ },
359+ {
360+ "fixture": "accuracy-fixture-model_layers_27_mlp_up_proj.pt",
361+ "fixture_sha256": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
362+ "m": 1024,
363+ "k": 1024,
364+ "n": 3072,
365+ "opsnn_padded_k": 2048,
366+ "opsnn_padded_n": 3072,
367+ "plain_native": {
368+ "nmse": 0.021787974624019088,
369+ "nrmse": 0.1476075019232393,
370+ "sqnr_db": 16.61783139211963,
371+ "cosine": 0.9896387374240014,
372+ "max_abs_error": 53.0
373+ },
374+ "native_scale_alg2": {
375+ "nmse": 0.025910815855607353,
376+ "nrmse": 0.16096836911520024,
377+ "sqnr_db": 15.865189121392245,
378+ "cosine": 0.9869727854323713,
379+ "max_abs_error": 33.734375
380+ },
381+ "native_scale_alg2_error": null,
382+ "tilelang_planned_macaq": {
383+ "nmse": 0.008336486324689736,
384+ "nrmse": 0.09130436092920062,
385+ "sqnr_db": 20.790169579159002,
386+ "cosine": 0.9959198014115227,
387+ "max_abs_error": 39.0
388+ },
389+ "tilelang_macaq": {
390+ "nmse": 0.008336486324689736,
391+ "nrmse": 0.09130436092920062,
392+ "sqnr_db": 20.790169579159002,
393+ "cosine": 0.9959198014115227,
394+ "max_abs_error": 39.0
395+ },
396+ "opsnn_macaq": {
397+ "nmse": 0.008336486324689736,
398+ "nrmse": 0.09130436092920062,
399+ "sqnr_db": 20.790169579159002,
400+ "cosine": 0.9959198014115227,
401+ "max_abs_error": 39.0
402+ },
403+ "cpu_reference_agreement": {
404+ "plain_max_abs": 0.0,
405+ "tilelang_max_abs": 0.0,
406+ "tilelang_planned_max_abs": 0.0,
407+ "opsnn_max_abs": 0.0
408+ }
409+ },
410+ {
411+ "fixture": "accuracy-fixture-model_layers_27_self_attn_q_proj.pt",
412+ "fixture_sha256": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
413+ "m": 1024,
414+ "k": 1024,
415+ "n": 2048,
416+ "opsnn_padded_k": 1536,
417+ "opsnn_padded_n": 2048,
418+ "plain_native": {
419+ "nmse": 0.014878039646034468,
420+ "nrmse": 0.12197556987378443,
421+ "sqnr_db": 18.27454288346345,
422+ "cosine": 0.9928836409767186,
423+ "max_abs_error": 32.5
424+ },
425+ "native_scale_alg2": {
426+ "nmse": 0.017160446816167834,
427+ "nrmse": 0.13099788859431222,
428+ "sqnr_db": 17.654714083713575,
429+ "cosine": 0.9913830249456285,
430+ "max_abs_error": 30.0
431+ },
432+ "native_scale_alg2_error": null,
433+ "tilelang_planned_macaq": {
434+ "nmse": 0.007906629422839765,
435+ "nrmse": 0.08891922976971722,
436+ "sqnr_db": 21.02008615747497,
437+ "cosine": 0.9961864477162093,
438+ "max_abs_error": 17.75
439+ },
440+ "tilelang_macaq": {
441+ "nmse": 0.007906629422839765,
442+ "nrmse": 0.08891922976971722,
443+ "sqnr_db": 21.02008615747497,
444+ "cosine": 0.9961864477162093,
445+ "max_abs_error": 17.75
446+ },
447+ "opsnn_macaq": {
448+ "nmse": 0.007906629422839765,
449+ "nrmse": 0.08891922976971722,
450+ "sqnr_db": 21.02008615747497,
451+ "cosine": 0.9961864477162093,
452+ "max_abs_error": 17.75
453+ },
454+ "cpu_reference_agreement": {
455+ "plain_max_abs": 0.0,
456+ "tilelang_max_abs": 0.0,
457+ "tilelang_planned_max_abs": 0.0,
458+ "opsnn_max_abs": 0.0
459+ }
460+ }
461+]
@@ -0,0 +1,39 @@
1+{
2+ "device": "Ascend950DT_9592",
3+ "torch": "2.9.0+cpu",
4+ "torch_npu": "2.9.0.post2",
5+ "opsnn_wheel_sha256": "b284336b70f82a80a4c2feba59bbc7f53cf178563f988dd89e527ef44ad50e06",
6+ "source_cpp_sha256": {
7+ "experimental/matmul/common/macaq/macaq_hadamard_mxfp4.hpp": "c62ab428e2d712d38b44e2e2de71605210e73b7fc4edac087a96a8aeb48c3574",
8+ "experimental/matmul/common/macaq/macaq_w4a4_kernel_impl.hpp": "52a5ed13b6798df7b36cdc08335663b2ffb70b52bda12180712b0dbb1ea1c26c",
9+ "experimental/matmul/macaq_w4a4_matmul/macaq_w4a4_matmul.cpp": "2ddea3d5dc3eed689a3aa59a43e219247b47344180a8ea23c24f94316a05ff44",
10+ "experimental/matmul/macaq_w4a4_grouped_matmul/macaq_w4a4_grouped_matmul.cpp": "63637c9de33517b69800b4dd0d748c17cbe5910facab4e5db39de7f931d38c93",
11+ "experimental/matmul/common/macaq/tests/test_macaq_raw_diagonal.py": "72f7a4536734be62e733656ce6cc45bd4b445529d995a224bc6cf309d24c7ed7"
12+ },
13+ "tilelang_base_commit": "b7d8b14c1e14f2412e4a37ccecde85e6284d0349",
14+ "model": "Qwen/Qwen3-0.6B",
15+ "checks": 36,
16+ "native_scale_alg2_checks": 9,
17+ "tilelang_source_sha256": {
18+ "__init__.py": "a81e80bbf9fd868d5109d2ab725dec9afe16d0a346ccad7809e55fb6dddfd2a7",
19+ "matmul/__init__.py": "13c8e8bdf2323d8787bcdf944464e1975343b35fe95a95e40d8d5612cec5a1eb",
20+ "matmul/macaq_w4a4_matmul.py": "039334d011a6c5714be28066c1dc12a00868ac4a9fea1c640ed974a61bf830b8",
21+ "matmul/macaq_w4a4_matmul_kernel.py": "fb33d479bb11db9ca3617c029d8c40dc7135af1baf0571346b6add11884bd777",
22+ "matmul/macaq_w4a4_global_kernel.py": "128169df74198a73da97292edc8d9aefe9caee6cfe70c3c2b2b88fe024c0d65c",
23+ "matmul/macaq_w4a4_dynamic_group_kernel.py": "c4a61194f87466de63e30b5f412146ce08f14eab7c5a1887cf83a2328b39212a"
24+ },
25+ "scope": "nine real projection fixtures, actual native and MACaQ NPU outputs vs CPU algorithm references; not whole-model NPU evaluation or model throughput",
26+ "padding": "ops-nn zero-pads K/N to supported pairs and slices original columns; zero padding preserves block32 transform boundaries; no latency claim for padded calls",
27+ "fixture_sha256": {
28+ "accuracy-fixture-model_layers_14_mlp_up_proj.pt": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
29+ "accuracy-fixture-model_layers_14_mlp_down_proj.pt": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
30+ "accuracy-fixture-model_layers_14_self_attn_q_proj.pt": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
31+ "accuracy-fixture-model_layers_27_self_attn_q_proj.pt": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
32+ "accuracy-fixture-model_layers_27_mlp_up_proj.pt": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
33+ "accuracy-fixture-model_layers_27_mlp_down_proj.pt": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
34+ "accuracy-fixture-model_layers_0_self_attn_q_proj.pt": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
35+ "accuracy-fixture-model_layers_0_mlp_down_proj.pt": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
36+ "accuracy-fixture-model_layers_0_mlp_up_proj.pt": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a"
37+ },
38+ "harness_sha256": "0daec03479f004eebb7e1099012d907933819f67bf76c916a9d3c180ce9d96ef"
39+}
@@ -0,0 +1,461 @@
1+[
2+ {
3+ "fixture": "accuracy-fixture-model_layers_0_mlp_down_proj.pt",
4+ "fixture_sha256": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
5+ "m": 1024,
6+ "k": 3072,
7+ "n": 1024,
8+ "opsnn_padded_k": 3072,
9+ "opsnn_padded_n": 7168,
10+ "plain_native": {
11+ "nmse": 0.030516970236956067,
12+ "nrmse": 0.17469107085640087,
13+ "sqnr_db": 15.154585858772782,
14+ "cosine": 0.9852403571117876,
15+ "max_abs_error": 0.25
16+ },
17+ "native_scale_alg2": {
18+ "nmse": 0.031153790077059946,
19+ "nrmse": 0.1765043627706124,
20+ "sqnr_db": 15.064891108210311,
21+ "cosine": 0.9843569751092435,
22+ "max_abs_error": 0.19921875
23+ },
24+ "native_scale_alg2_error": null,
25+ "tilelang_planned_macaq": {
26+ "nmse": 0.018508736055048453,
27+ "nrmse": 0.13604681567404822,
28+ "sqnr_db": 17.326232378143693,
29+ "cosine": 0.9908084532765248,
30+ "max_abs_error": 0.248046875
31+ },
32+ "tilelang_macaq": {
33+ "nmse": 0.018508736055048453,
34+ "nrmse": 0.13604681567404822,
35+ "sqnr_db": 17.326232378143693,
36+ "cosine": 0.9908084532765248,
37+ "max_abs_error": 0.248046875
38+ },
39+ "opsnn_macaq": {
40+ "nmse": 0.018508736055048453,
41+ "nrmse": 0.13604681567404822,
42+ "sqnr_db": 17.326232378143693,
43+ "cosine": 0.9908084532765248,
44+ "max_abs_error": 0.248046875
45+ },
46+ "cpu_reference_agreement": {
47+ "plain_max_abs": 0.0,
48+ "tilelang_max_abs": 0.0,
49+ "tilelang_planned_max_abs": 0.0,
50+ "opsnn_max_abs": 0.0
51+ }
52+ },
53+ {
54+ "fixture": "accuracy-fixture-model_layers_0_mlp_up_proj.pt",
55+ "fixture_sha256": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a",
56+ "m": 1024,
57+ "k": 1024,
58+ "n": 3072,
59+ "opsnn_padded_k": 2048,
60+ "opsnn_padded_n": 3072,
61+ "plain_native": {
62+ "nmse": 0.03272208139022038,
63+ "nrmse": 0.18089245807998844,
64+ "sqnr_db": 14.85159079464714,
65+ "cosine": 0.9837271166985933,
66+ "max_abs_error": 0.640625
67+ },
68+ "native_scale_alg2": {
69+ "nmse": 0.04013932103835252,
70+ "nrmse": 0.20034799983616638,
71+ "sqnr_db": 13.964299779320108,
72+ "cosine": 0.9798668105571983,
73+ "max_abs_error": 0.546875
74+ },
75+ "native_scale_alg2_error": null,
76+ "tilelang_planned_macaq": {
77+ "nmse": 0.018918712122045826,
78+ "nrmse": 0.13754530934221576,
79+ "sqnr_db": 17.231084312178428,
80+ "cosine": 0.9905704452715268,
81+ "max_abs_error": 0.3671875
82+ },
83+ "tilelang_macaq": {
84+ "nmse": 0.018918712122045826,
85+ "nrmse": 0.13754530934221576,
86+ "sqnr_db": 17.231084312178428,
87+ "cosine": 0.9905704452715268,
88+ "max_abs_error": 0.3671875
89+ },
90+ "opsnn_macaq": {
91+ "nmse": 0.018918712122045826,
92+ "nrmse": 0.13754530934221576,
93+ "sqnr_db": 17.231084312178428,
94+ "cosine": 0.9905704452715268,
95+ "max_abs_error": 0.3671875
96+ },
97+ "cpu_reference_agreement": {
98+ "plain_max_abs": 0.0,
99+ "tilelang_max_abs": 0.0,
100+ "tilelang_planned_max_abs": 0.0,
101+ "opsnn_max_abs": 0.0
102+ }
103+ },
104+ {
105+ "fixture": "accuracy-fixture-model_layers_0_self_attn_q_proj.pt",
106+ "fixture_sha256": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
107+ "m": 1024,
108+ "k": 1024,
109+ "n": 2048,
110+ "opsnn_padded_k": 1536,
111+ "opsnn_padded_n": 2048,
112+ "plain_native": {
113+ "nmse": 0.012961810244357238,
114+ "nrmse": 0.11384994617634757,
115+ "sqnr_db": 18.873343407313314,
116+ "cosine": 0.9945141181596306,
117+ "max_abs_error": 1.015625
118+ },
119+ "native_scale_alg2": {
120+ "nmse": 0.011486990046041059,
121+ "nrmse": 0.10717737655886647,
122+ "sqnr_db": 19.39793755266881,
123+ "cosine": 0.9943654953511734,
124+ "max_abs_error": 1.20703125
125+ },
126+ "native_scale_alg2_error": null,
127+ "tilelang_planned_macaq": {
128+ "nmse": 0.005795284495877784,
129+ "nrmse": 0.07612676596229334,
130+ "sqnr_db": 22.36925239259129,
131+ "cosine": 0.9972342905702456,
132+ "max_abs_error": 0.46875
133+ },
134+ "tilelang_macaq": {
135+ "nmse": 0.005795284495877784,
136+ "nrmse": 0.07612676596229334,
137+ "sqnr_db": 22.36925239259129,
138+ "cosine": 0.9972342905702456,
139+ "max_abs_error": 0.46875
140+ },
141+ "opsnn_macaq": {
142+ "nmse": 0.005795284495877784,
143+ "nrmse": 0.07612676596229334,
144+ "sqnr_db": 22.36925239259129,
145+ "cosine": 0.9972342905702456,
146+ "max_abs_error": 0.46875
147+ },
148+ "cpu_reference_agreement": {
149+ "plain_max_abs": 0.0,
150+ "tilelang_max_abs": 0.0,
151+ "tilelang_planned_max_abs": 0.0,
152+ "opsnn_max_abs": 0.0
153+ }
154+ },
155+ {
156+ "fixture": "accuracy-fixture-model_layers_14_mlp_down_proj.pt",
157+ "fixture_sha256": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
158+ "m": 1024,
159+ "k": 3072,
160+ "n": 1024,
161+ "opsnn_padded_k": 3072,
162+ "opsnn_padded_n": 7168,
163+ "plain_native": {
164+ "nmse": 0.03410957884917448,
165+ "nrmse": 0.18468778749331122,
166+ "sqnr_db": 14.671236427916272,
167+ "cosine": 0.9830276128202399,
168+ "max_abs_error": 1.5625
169+ },
170+ "native_scale_alg2": {
171+ "nmse": 0.03799854210203062,
172+ "nrmse": 0.19493214743092177,
173+ "sqnr_db": 14.202330657302781,
174+ "cosine": 0.9809640218643827,
175+ "max_abs_error": 1.8125
176+ },
177+ "native_scale_alg2_error": null,
178+ "tilelang_planned_macaq": {
179+ "nmse": 0.021642116309140973,
180+ "nrmse": 0.1471125973842518,
181+ "sqnr_db": 16.647002733047213,
182+ "cosine": 0.989176496558601,
183+ "max_abs_error": 0.7265625
184+ },
185+ "tilelang_macaq": {
186+ "nmse": 0.021642116309140973,
187+ "nrmse": 0.1471125973842518,
188+ "sqnr_db": 16.647002733047213,
189+ "cosine": 0.989176496558601,
190+ "max_abs_error": 0.7265625
191+ },
192+ "opsnn_macaq": {
193+ "nmse": 0.021642116309140973,
194+ "nrmse": 0.1471125973842518,
195+ "sqnr_db": 16.647002733047213,
196+ "cosine": 0.989176496558601,
197+ "max_abs_error": 0.7265625
198+ },
199+ "cpu_reference_agreement": {
200+ "plain_max_abs": 0.0,
201+ "tilelang_max_abs": 0.0,
202+ "tilelang_planned_max_abs": 0.0,
203+ "opsnn_max_abs": 0.0
204+ }
205+ },
206+ {
207+ "fixture": "accuracy-fixture-model_layers_14_mlp_up_proj.pt",
208+ "fixture_sha256": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
209+ "m": 1024,
210+ "k": 1024,
211+ "n": 3072,
212+ "opsnn_padded_k": 2048,
213+ "opsnn_padded_n": 3072,
214+ "plain_native": {
215+ "nmse": 0.027274659838753348,
216+ "nrmse": 0.16515041579951698,
217+ "sqnr_db": 15.642406570942896,
218+ "cosine": 0.9865070511505231,
219+ "max_abs_error": 1.109375
220+ },
221+ "native_scale_alg2": {
222+ "nmse": 0.030852923399939662,
223+ "nrmse": 0.17565000256174113,
224+ "sqnr_db": 15.107036790761057,
225+ "cosine": 0.9845036092016929,
226+ "max_abs_error": 1.03125
227+ },
228+ "native_scale_alg2_error": null,
229+ "tilelang_planned_macaq": {
230+ "nmse": 0.01696913017803275,
231+ "nrmse": 0.13026561395100686,
232+ "sqnr_db": 17.7034041864651,
233+ "cosine": 0.9915783593889278,
234+ "max_abs_error": 0.671875
235+ },
236+ "tilelang_macaq": {
237+ "nmse": 0.01696913017803275,
238+ "nrmse": 0.13026561395100686,
239+ "sqnr_db": 17.7034041864651,
240+ "cosine": 0.9915783593889278,
241+ "max_abs_error": 0.671875
242+ },
243+ "opsnn_macaq": {
244+ "nmse": 0.01696913017803275,
245+ "nrmse": 0.13026561395100686,
246+ "sqnr_db": 17.7034041864651,
247+ "cosine": 0.9915783593889278,
248+ "max_abs_error": 0.671875
249+ },
250+ "cpu_reference_agreement": {
251+ "plain_max_abs": 0.0,
252+ "tilelang_max_abs": 0.0,
253+ "tilelang_planned_max_abs": 0.0,
254+ "opsnn_max_abs": 0.0
255+ }
256+ },
257+ {
258+ "fixture": "accuracy-fixture-model_layers_14_self_attn_q_proj.pt",
259+ "fixture_sha256": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
260+ "m": 1024,
261+ "k": 1024,
262+ "n": 2048,
263+ "opsnn_padded_k": 1536,
264+ "opsnn_padded_n": 2048,
265+ "plain_native": {
266+ "nmse": 0.01466745110141977,
267+ "nrmse": 0.12110925274899424,
268+ "sqnr_db": 18.33645350967023,
269+ "cosine": 0.9930062509087988,
270+ "max_abs_error": 2.640625
271+ },
272+ "native_scale_alg2": {
273+ "nmse": 0.01625560235156519,
274+ "nrmse": 0.12749746017691957,
275+ "sqnr_db": 17.88996933081782,
276+ "cosine": 0.9918593472312802,
277+ "max_abs_error": 3.3125
278+ },
279+ "native_scale_alg2_error": null,
280+ "tilelang_planned_macaq": {
281+ "nmse": 0.0075766859551332265,
282+ "nrmse": 0.08704416094795346,
283+ "sqnr_db": 21.205207133813268,
284+ "cosine": 0.9962798805014916,
285+ "max_abs_error": 2.1171875
286+ },
287+ "tilelang_macaq": {
288+ "nmse": 0.0075766859551332265,
289+ "nrmse": 0.08704416094795346,
290+ "sqnr_db": 21.205207133813268,
291+ "cosine": 0.9962798805014916,
292+ "max_abs_error": 2.1171875
293+ },
294+ "opsnn_macaq": {
295+ "nmse": 0.0075766859551332265,
296+ "nrmse": 0.08704416094795346,
297+ "sqnr_db": 21.205207133813268,
298+ "cosine": 0.9962798805014916,
299+ "max_abs_error": 2.1171875
300+ },
301+ "cpu_reference_agreement": {
302+ "plain_max_abs": 0.0,
303+ "tilelang_max_abs": 0.0,
304+ "tilelang_planned_max_abs": 0.0,
305+ "opsnn_max_abs": 0.0
306+ }
307+ },
308+ {
309+ "fixture": "accuracy-fixture-model_layers_27_mlp_down_proj.pt",
310+ "fixture_sha256": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
311+ "m": 1024,
312+ "k": 3072,
313+ "n": 1024,
314+ "opsnn_padded_k": 3072,
315+ "opsnn_padded_n": 7168,
316+ "plain_native": {
317+ "nmse": 0.021753115704479336,
318+ "nrmse": 0.14748937488673322,
319+ "sqnr_db": 16.62478530141382,
320+ "cosine": 0.9903826287274079,
321+ "max_abs_error": 720.0
322+ },
323+ "native_scale_alg2": {
324+ "nmse": 0.019562300238837857,
325+ "nrmse": 0.13986529318897473,
326+ "sqnr_db": 17.085800799012137,
327+ "cosine": 0.990239036351425,
328+ "max_abs_error": 192.0
329+ },
330+ "native_scale_alg2_error": null,
331+ "tilelang_planned_macaq": {
332+ "nmse": 0.0047220473550336605,
333+ "nrmse": 0.06871715473616222,
334+ "sqnr_db": 23.258696619149188,
335+ "cosine": 0.9980580611788563,
336+ "max_abs_error": 288.0
337+ },
338+ "tilelang_macaq": {
339+ "nmse": 0.0047220473550336605,
340+ "nrmse": 0.06871715473616222,
341+ "sqnr_db": 23.258696619149188,
342+ "cosine": 0.9980580611788563,
343+ "max_abs_error": 288.0
344+ },
345+ "opsnn_macaq": {
346+ "nmse": 0.0047220473550336605,
347+ "nrmse": 0.06871715473616222,
348+ "sqnr_db": 23.258696619149188,
349+ "cosine": 0.9980580611788563,
350+ "max_abs_error": 288.0
351+ },
352+ "cpu_reference_agreement": {
353+ "plain_max_abs": 0.0,
354+ "tilelang_max_abs": 0.0,
355+ "tilelang_planned_max_abs": 0.0,
356+ "opsnn_max_abs": 0.0
357+ }
358+ },
359+ {
360+ "fixture": "accuracy-fixture-model_layers_27_mlp_up_proj.pt",
361+ "fixture_sha256": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
362+ "m": 1024,
363+ "k": 1024,
364+ "n": 3072,
365+ "opsnn_padded_k": 2048,
366+ "opsnn_padded_n": 3072,
367+ "plain_native": {
368+ "nmse": 0.021787974624019088,
369+ "nrmse": 0.1476075019232393,
370+ "sqnr_db": 16.61783139211963,
371+ "cosine": 0.9896387374240014,
372+ "max_abs_error": 53.0
373+ },
374+ "native_scale_alg2": {
375+ "nmse": 0.025910815855607353,
376+ "nrmse": 0.16096836911520024,
377+ "sqnr_db": 15.865189121392245,
378+ "cosine": 0.9869727854323713,
379+ "max_abs_error": 33.734375
380+ },
381+ "native_scale_alg2_error": null,
382+ "tilelang_planned_macaq": {
383+ "nmse": 0.008336486324689736,
384+ "nrmse": 0.09130436092920062,
385+ "sqnr_db": 20.790169579159002,
386+ "cosine": 0.9959198014115227,
387+ "max_abs_error": 39.0
388+ },
389+ "tilelang_macaq": {
390+ "nmse": 0.008336486324689736,
391+ "nrmse": 0.09130436092920062,
392+ "sqnr_db": 20.790169579159002,
393+ "cosine": 0.9959198014115227,
394+ "max_abs_error": 39.0
395+ },
396+ "opsnn_macaq": {
397+ "nmse": 0.008336486324689736,
398+ "nrmse": 0.09130436092920062,
399+ "sqnr_db": 20.790169579159002,
400+ "cosine": 0.9959198014115227,
401+ "max_abs_error": 39.0
402+ },
403+ "cpu_reference_agreement": {
404+ "plain_max_abs": 0.0,
405+ "tilelang_max_abs": 0.0,
406+ "tilelang_planned_max_abs": 0.0,
407+ "opsnn_max_abs": 0.0
408+ }
409+ },
410+ {
411+ "fixture": "accuracy-fixture-model_layers_27_self_attn_q_proj.pt",
412+ "fixture_sha256": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
413+ "m": 1024,
414+ "k": 1024,
415+ "n": 2048,
416+ "opsnn_padded_k": 1536,
417+ "opsnn_padded_n": 2048,
418+ "plain_native": {
419+ "nmse": 0.014878039646034468,
420+ "nrmse": 0.12197556987378443,
421+ "sqnr_db": 18.27454288346345,
422+ "cosine": 0.9928836409767186,
423+ "max_abs_error": 32.5
424+ },
425+ "native_scale_alg2": {
426+ "nmse": 0.017160446816167834,
427+ "nrmse": 0.13099788859431222,
428+ "sqnr_db": 17.654714083713575,
429+ "cosine": 0.9913830249456285,
430+ "max_abs_error": 30.0
431+ },
432+ "native_scale_alg2_error": null,
433+ "tilelang_planned_macaq": {
434+ "nmse": 0.007906629422839765,
435+ "nrmse": 0.08891922976971722,
436+ "sqnr_db": 21.02008615747497,
437+ "cosine": 0.9961864477162093,
438+ "max_abs_error": 17.75
439+ },
440+ "tilelang_macaq": {
441+ "nmse": 0.007906629422839765,
442+ "nrmse": 0.08891922976971722,
443+ "sqnr_db": 21.02008615747497,
444+ "cosine": 0.9961864477162093,
445+ "max_abs_error": 17.75
446+ },
447+ "opsnn_macaq": {
448+ "nmse": 0.007906629422839765,
449+ "nrmse": 0.08891922976971722,
450+ "sqnr_db": 21.02008615747497,
451+ "cosine": 0.9961864477162093,
452+ "max_abs_error": 17.75
453+ },
454+ "cpu_reference_agreement": {
455+ "plain_max_abs": 0.0,
456+ "tilelang_max_abs": 0.0,
457+ "tilelang_planned_max_abs": 0.0,
458+ "opsnn_max_abs": 0.0
459+ }
460+ }
461+]
@@ -0,0 +1,38 @@
1+{
2+ "device": "Ascend950DT_9592",
3+ "torch": "2.9.0+cpu",
4+ "torch_npu": "2.9.0.post2",
5+ "opsnn_wheel_sha256": "b284336b70f82a80a4c2feba59bbc7f53cf178563f988dd89e527ef44ad50e06",
6+ "source_cpp_sha256": {
7+ "experimental/matmul/common/macaq/macaq_hadamard_mxfp4.hpp": "c62ab428e2d712d38b44e2e2de71605210e73b7fc4edac087a96a8aeb48c3574",
8+ "experimental/matmul/common/macaq/macaq_w4a4_kernel_impl.hpp": "52a5ed13b6798df7b36cdc08335663b2ffb70b52bda12180712b0dbb1ea1c26c",
9+ "experimental/matmul/macaq_w4a4_matmul/macaq_w4a4_matmul.cpp": "2ddea3d5dc3eed689a3aa59a43e219247b47344180a8ea23c24f94316a05ff44",
10+ "experimental/matmul/macaq_w4a4_grouped_matmul/macaq_w4a4_grouped_matmul.cpp": "63637c9de33517b69800b4dd0d748c17cbe5910facab4e5db39de7f931d38c93",
11+ "experimental/matmul/common/macaq/tests/test_macaq_raw_diagonal.py": "72f7a4536734be62e733656ce6cc45bd4b445529d995a224bc6cf309d24c7ed7"
12+ },
13+ "tilelang_base_commit": "b7d8b14c1e14f2412e4a37ccecde85e6284d0349",
14+ "model": "Qwen/Qwen3-0.6B",
15+ "checks": 36,
16+ "native_scale_alg2_checks": 9,
17+ "tilelang_source_sha256": {
18+ "__init__.py": "a81e80bbf9fd868d5109d2ab725dec9afe16d0a346ccad7809e55fb6dddfd2a7",
19+ "matmul/__init__.py": "13c8e8bdf2323d8787bcdf944464e1975343b35fe95a95e40d8d5612cec5a1eb",
20+ "matmul/macaq_w4a4_matmul.py": "039334d011a6c5714be28066c1dc12a00868ac4a9fea1c640ed974a61bf830b8",
21+ "matmul/macaq_w4a4_matmul_kernel.py": "fb33d479bb11db9ca3617c029d8c40dc7135af1baf0571346b6add11884bd777",
22+ "matmul/macaq_w4a4_global_kernel.py": "8ad67823f4711ed04665a98bf2c00575a1604f1a7b4a4dd3df90dcfbfe707ebc"
23+ },
24+ "scope": "nine real projection fixtures, actual native and MACaQ NPU outputs vs CPU algorithm references; not whole-model NPU evaluation or model throughput",
25+ "padding": "ops-nn zero-pads K/N to supported pairs and slices original columns; zero padding preserves block32 transform boundaries; no latency claim for padded calls",
26+ "fixture_sha256": {
27+ "accuracy-fixture-model_layers_14_mlp_up_proj.pt": "93015e6f4ed06d62306d6fccfc75c3fa8a2462740a20c61c72c8b4871668986d",
28+ "accuracy-fixture-model_layers_14_mlp_down_proj.pt": "06327450f71e490385a6137915d300273b901ed344017c98b3cfaf8a7061b579",
29+ "accuracy-fixture-model_layers_14_self_attn_q_proj.pt": "abe62ae90b968c85dfc57dbfa8bd287a1672b9a7ba9431570a121b1cff9fbb28",
30+ "accuracy-fixture-model_layers_27_self_attn_q_proj.pt": "2ea2b3baf308ff4f1f81f978b28137ef5e98c111166fc24e8b2d6bb9aab7f391",
31+ "accuracy-fixture-model_layers_27_mlp_up_proj.pt": "e6ec478d4b4190fdef10af43e0f09cf14b869eb66bb3dcfa80f91bf0a6681297",
32+ "accuracy-fixture-model_layers_27_mlp_down_proj.pt": "18f102d83016adb97aa542df1515be28ab7acea4059b91fcd8acb22427382c25",
33+ "accuracy-fixture-model_layers_0_self_attn_q_proj.pt": "6ddc2c4ab7cccf3de0b083bb5ccb22cde417e5b4ed3ce81cd2659a579b18076c",
34+ "accuracy-fixture-model_layers_0_mlp_down_proj.pt": "4f73bdf7d8a927172fea0866e27cbe850c894deb329930bd08b99aab6cff444c",
35+ "accuracy-fixture-model_layers_0_mlp_up_proj.pt": "03b5ea72441a092958e49baa3ec5fe84ec79cd897de2d7d1e3a4e54a7581d92a"
36+ },
37+ "harness_sha256": "b6ec7a9498e46bdc07ecd93e2e2b1aa1a8e6fb4a2ff5b49405abae87967ce146"
38+}
Aexperimental/matmul/common/macaq/benchmark/accuracy-npu-projections.csv+10-0File content is under review, please try again later
@@ -0,0 +1,3 @@
1+version https://git-lfs.github.com/spec/v1
2+oid sha256:fc034e7b2366698126d47f82d80bbbf5bc236837bd242dbc1526b9b1ff14c92d
3+size 99367
@@ -0,0 +1,3 @@
1+version https://git-lfs.github.com/spec/v1
2+oid sha256:4a810d54ebcb5e75cd8e5b0faea20408e7bccbb0f03f235a62e2317aa68080ce
3+size 91221
@@ -0,0 +1,266 @@
1+{
2+ "bf16": {
3+ "chunks": [
4+ {
5+ "chunk": 0,
6+ "scored_tokens": 1023,
7+ "nll": 2613.495315551758
8+ },
9+ {
10+ "chunk": 1,
11+ "scored_tokens": 1023,
12+ "nll": 3464.470916748047
13+ },
14+ {
15+ "chunk": 2,
16+ "scored_tokens": 1023,
17+ "nll": 3268.416778564453
18+ },
19+ {
20+ "chunk": 3,
21+ "scored_tokens": 1023,
22+ "nll": 3495.12353515625
23+ },
24+ {
25+ "chunk": 4,
26+ "scored_tokens": 1023,
27+ "nll": 3786.4422912597656
28+ },
29+ {
30+ "chunk": 5,
31+ "scored_tokens": 1023,
32+ "nll": 3405.630157470703
33+ },
34+ {
35+ "chunk": 6,
36+ "scored_tokens": 1023,
37+ "nll": 3722.502685546875
38+ },
39+ {
40+ "chunk": 7,
41+ "scored_tokens": 1023,
42+ "nll": 3582.7979125976562
43+ },
44+ {
45+ "chunk": 8,
46+ "scored_tokens": 1023,
47+ "nll": 2805.970687866211
48+ },
49+ {
50+ "chunk": 9,
51+ "scored_tokens": 1023,
52+ "nll": 3496.6533813476562
53+ },
54+ {
55+ "chunk": 10,
56+ "scored_tokens": 1023,
57+ "nll": 2920.6666870117188
58+ },
59+ {
60+ "chunk": 11,
61+ "scored_tokens": 1023,
62+ "nll": 2406.7943420410156
63+ },
64+ {
65+ "chunk": 12,
66+ "scored_tokens": 1023,
67+ "nll": 2533.4830017089844
68+ },
69+ {
70+ "chunk": 13,
71+ "scored_tokens": 1023,
72+ "nll": 2393.1245727539062
73+ },
74+ {
75+ "chunk": 14,
76+ "scored_tokens": 1023,
77+ "nll": 3081.54541015625
78+ },
79+ {
80+ "chunk": 15,
81+ "scored_tokens": 1023,
82+ "nll": 3096.2925720214844
83+ }
84+ ],
85+ "nll_sum": 50073.410247802734,
86+ "scored_tokens": 16368,
87+ "elapsed_cpu_seconds": 80.64238631998887,
88+ "perplexity": 21.31105482145711
89+ },
90+ "plain_mxfp4_w4a4": {
91+ "chunks": [
92+ {
93+ "chunk": 0,
94+ "scored_tokens": 1023,
95+ "nll": 2993.995475769043
96+ },
97+ {
98+ "chunk": 1,
99+ "scored_tokens": 1023,
100+ "nll": 3964.547393798828
101+ },
102+ {
103+ "chunk": 2,
104+ "scored_tokens": 1023,
105+ "nll": 3789.380096435547
106+ },
107+ {
108+ "chunk": 3,
109+ "scored_tokens": 1023,
110+ "nll": 3984.91650390625
111+ },
112+ {
113+ "chunk": 4,
114+ "scored_tokens": 1023,
115+ "nll": 4248.028869628906
116+ },
117+ {
118+ "chunk": 5,
119+ "scored_tokens": 1023,
120+ "nll": 3814.5045471191406
121+ },
122+ {
123+ "chunk": 6,
124+ "scored_tokens": 1023,
125+ "nll": 4285.850921630859
126+ },
127+ {
128+ "chunk": 7,
129+ "scored_tokens": 1023,
130+ "nll": 4122.245635986328
131+ },
132+ {
133+ "chunk": 8,
134+ "scored_tokens": 1023,
135+ "nll": 3248.092559814453
136+ },
137+ {
138+ "chunk": 9,
139+ "scored_tokens": 1023,
140+ "nll": 4024.273223876953
141+ },
142+ {
143+ "chunk": 10,
144+ "scored_tokens": 1023,
145+ "nll": 3406.539581298828
146+ },
147+ {
148+ "chunk": 11,
149+ "scored_tokens": 1023,
150+ "nll": 2750.1438598632812
151+ },
152+ {
153+ "chunk": 12,
154+ "scored_tokens": 1023,
155+ "nll": 2889.586441040039
156+ },
157+ {
158+ "chunk": 13,
159+ "scored_tokens": 1023,
160+ "nll": 2764.8697509765625
161+ },
162+ {
163+ "chunk": 14,
164+ "scored_tokens": 1023,
165+ "nll": 3561.8204956054688
166+ },
167+ {
168+ "chunk": 15,
169+ "scored_tokens": 1023,
170+ "nll": 3593.2583923339844
171+ }
172+ ],
173+ "nll_sum": 57442.05374908447,
174+ "scored_tokens": 16368,
175+ "elapsed_cpu_seconds": 100.81584860995645,
176+ "perplexity": 33.42860217079505
177+ },
178+ "macaq_w4a4": {
179+ "chunks": [
180+ {
181+ "chunk": 0,
182+ "scored_tokens": 1023,
183+ "nll": 2781.291793823242
184+ },
185+ {
186+ "chunk": 1,
187+ "scored_tokens": 1023,
188+ "nll": 3652.1476440429688
189+ },
190+ {
191+ "chunk": 2,
192+ "scored_tokens": 1023,
193+ "nll": 3466.021270751953
194+ },
195+ {
196+ "chunk": 3,
197+ "scored_tokens": 1023,
198+ "nll": 3660.3853759765625
199+ },
200+ {
201+ "chunk": 4,
202+ "scored_tokens": 1023,
203+ "nll": 3981.515594482422
204+ },
205+ {
206+ "chunk": 5,
207+ "scored_tokens": 1023,
208+ "nll": 3621.0074157714844
209+ },
210+ {
211+ "chunk": 6,
212+ "scored_tokens": 1023,
213+ "nll": 3980.6835021972656
214+ },
215+ {
216+ "chunk": 7,
217+ "scored_tokens": 1023,
218+ "nll": 3748.3545837402344
219+ },
220+ {
221+ "chunk": 8,
222+ "scored_tokens": 1023,
223+ "nll": 2963.4041137695312
224+ },
225+ {
226+ "chunk": 9,
227+ "scored_tokens": 1023,
228+ "nll": 3685.198028564453
229+ },
230+ {
231+ "chunk": 10,
232+ "scored_tokens": 1023,
233+ "nll": 3102.4110717773438
234+ },
235+ {
236+ "chunk": 11,
237+ "scored_tokens": 1023,
238+ "nll": 2573.624221801758
239+ },
240+ {
241+ "chunk": 12,
242+ "scored_tokens": 1023,
243+ "nll": 2685.5667114257812
244+ },
245+ {
246+ "chunk": 13,
247+ "scored_tokens": 1023,
248+ "nll": 2548.2555541992188
249+ },
250+ {
251+ "chunk": 14,
252+ "scored_tokens": 1023,
253+ "nll": 3272.051513671875
254+ },
255+ {
256+ "chunk": 15,
257+ "scored_tokens": 1023,
258+ "nll": 3286.328125
259+ }
260+ ],
261+ "nll_sum": 53008.246520996094,
262+ "scored_tokens": 16368,
263+ "elapsed_cpu_seconds": 102.51845485001104,
264+ "perplexity": 25.496195250101927
265+ }
266+}
@@ -0,0 +1,21 @@
1+{
2+ "model": "Qwen/Qwen3-0.6B",
3+ "revision": "c1899de289a04d12100db370d81485cdf75e47ca",
4+ "execution": "CPU reference quantization-model PPL; not actual NPU full-model execution",
5+ "dataset": "Salesforce/wikitext wikitext-2-raw-v1",
6+ "context": 1024,
7+ "calibration_tokens": 1024,
8+ "heldout_tokens": 16384,
9+ "scored_tokens": 16368,
10+ "token_sha256": {
11+ "train": "ea0c105aae5e1f26ceb3a387594b84f26c4e53dc1ddaccdc2f15d68751f917e9",
12+ "test": "a404e545152236c323bdaddd73c18b4b210bd67c5e5f4f811701db84f54d5217"
13+ },
14+ "quantized_decoder_linears": 196,
15+ "embedding_and_lm_head": "BF16 in all arms",
16+ "calibration": "BF16 decoder activation capture, per-linear; same fixed calibration tokens; MACaQ alpha=.75 ridge=1 flip_iters=8 exponent_offsets=1,0,-1; no held-out tuning",
17+ "accuracy": "ordinary W4A4 and MACaQ W4A4 use exact Ascend CPU reference activation quantization and BF16 butterfly rules; weight codes use published pure-Torch calibrator",
18+ "method_sha256": "f53f40ddd4006c43dde6a7fbc7f43b2f210ce2320f73562ef96bc6681401bc59",
19+ "reference_sha256": "f65f8d3229339fba1a1762edd0bbd9825e534690f15099185fc0eea1452b67f6",
20+ "torch": "2.9.0+cpu"
21+}
Aexperimental/matmul/common/macaq/benchmark/accuracy.md+56-0File content is under review, please try again later
@@ -0,0 +1,3 @@
1+version https://git-lfs.github.com/spec/v1
2+oid sha256:6864ba86903ece8e2840afa6c622b7f2626581324070868f65db403e27a6db3d
3+size 163540
@@ -0,0 +1,3 @@
1+version https://git-lfs.github.com/spec/v1
2+oid sha256:271a6f4d0ed99b750232db52451473509eba529bd1e3689f48a24c55bebf4969
3+size 178848
@@ -0,0 +1,49 @@
1+{
2+ "source_commits": {
3+ "ops-nn": "09ed381118aeab506fb7219daf85f3d20b6d50ef",
4+ "ops-tilelang": "b7d8b14c1e14f2412e4a37ccecde85e6284d0349"
5+ },
6+ "extension_wheel_sha256": "06058f56e8688cc6d4d5c89c4e146f4d9cd15e20872be399ae6d1298d23fb08a",
7+ "torch": "2.9.0+cpu",
8+ "torch_npu": "2.9.0.post2",
9+ "tilelang": "0.1.15",
10+ "baselines": [
11+ "plain",
12+ "staged"
13+ ],
14+ "samples": 5,
15+ "repeats": 30,
16+ "timing": "sum of msprof device kernel durations per invocation, excluding cache flush; separate synchronized host call timing",
17+ "preparation": "TileLang normalized diagonal and weight scale layout prepared once; ops-nn preparation inside extension call is included",
18+ "harness_sha256": "3bcff7ad8ec2a8b6c4d8458a1d55968351ad0733eae4a99b2bcbd087963b4fd9",
19+ "profiler_sha256": "e322b8e09d2e1e3565093bcd6e332316426a4a596375db131d04096a3feef7f9",
20+ "device_name": "Ascend950DT_9592",
21+ "device_assignment": {
22+ "cases_0_to_47": "card A",
23+ "cases_48_to_83": "card B",
24+ "cases_84_to_95": "card A"
25+ },
26+ "primary_comparison": "MACaQ fused public API vs independent native CANN dynamic MXFP4 quantization + dense/grouped matmul (ascendc_plain), which omits MACaQ transform",
27+ "primary_metric": "repeated synchronized elapsed eager public-API brackets; all outputs allocated inside call",
28+ "elapsed_sweep": {
29+ "harness_sha256": "25c7899224525617b1147305b93247c4dc5c2b039130423c3d44f0ae6fc42a9c",
30+ "imported_harness_sha256": "3bcff7ad8ec2a8b6c4d8458a1d55968351ad0733eae4a99b2bcbd087963b4fd9",
31+ "trials": 15,
32+ "launches_per_trial": 20,
33+ "warmups_per_arm": 20,
34+ "input_pool": "two distinct activation buffers with identical deterministic values; alternate buffers each call",
35+ "timing": "synchronized wall brackets of 20 eager public API calls; arm order rotates each trial; no cache flush",
36+ "allocation": "all three arms allocate a fresh output inside every timed call; intermediate allocations included",
37+ "preparation": "static packed weights, scale views and TileLang diagonal prepared once; ops-nn internal per-call diagonal preparation included"
38+ },
39+ "elapsed_device_assignment": {
40+ "cases_0_to_47": "card A",
41+ "cases_48_to_95": "card B"
42+ },
43+ "toolkit": "CANN 9.3.0 weekly.20261021.01 / V100R001C13B023",
44+ "profiled_sweep_output_checks": 384,
45+ "elapsed_sweep_output_checks": 576,
46+ "configurations": 96,
47+ "elapsed_evidence_sha256": "b2eb930a843c8f7b49ee895e0eff53ad4e05ee37c2f9e60950343e5a13a95b02",
48+ "evidence_sha256": "fa56ba61163624fd1c8244fe1981e2a99f429266a64237cb602c4c53f75d13c6"
49+}
Aexperimental/matmul/common/macaq/benchmark/ops_nn_extension-elapsed.metadata.json+58-0File content is under review, please try again later
@@ -0,0 +1,3 @@
1+version https://git-lfs.github.com/spec/v1
2+oid sha256:9a0a48c6b4427191ead51227bfe1189bf7df5069e351946c9402ae16f6f7df55
3+size 159905
@@ -0,0 +1,3 @@
1+version https://git-lfs.github.com/spec/v1
2+oid sha256:87b390ccaada3bf787aa588857875a168d7cc6abfa3b09e567d2990c31b3a746
3+size 144177
Aexperimental/matmul/common/macaq/benchmark/ops_nn_extension-performance.md+125-0File content is under review, please try again later
Aexperimental/matmul/common/macaq/benchmark/submitted-source-before-optimization.md+339-0File content is under review, please try again later
Aexperimental/matmul/common/macaq/macaq_hadamard_mxfp4.hpp+1192-0File content is under review, please try again later
Aexperimental/matmul/common/macaq/macaq_op_includes.hpp+40-0File content is under review, please try again later
Aexperimental/matmul/common/macaq/macaq_w4a4_kernel_impl.hpp+1116-0File content is under review, please try again later
Aexperimental/matmul/common/macaq/tests/test_macaq_raw_diagonal.py+90-0File content is under review, please try again later
Aexperimental/matmul/macaq_w4a4_grouped_matmul/README.md+161-0File content is under review, please try again later
Aexperimental/matmul/macaq_w4a4_grouped_matmul/macaq_w4a4_grouped_matmul.cpp+196-0File content is under review, please try again later
Aexperimental/matmul/macaq_w4a4_grouped_matmul/tests/test_macaq_w4a4_grouped_matmul.py+167-0File content is under review, please try again later
Aexperimental/matmul/macaq_w4a4_matmul/README.md+152-0File content is under review, please try again later
Aexperimental/matmul/macaq_w4a4_matmul/macaq_w4a4_matmul.cpp+176-0File content is under review, please try again later
Aexperimental/matmul/macaq_w4a4_matmul/tests/test_macaq_w4a4_matmul.py+131-0File content is under review, please try again later
Mscripts/ci/compile_ascend950_pkg.sh+41-12File content is under review, please try again later