[L2] fix: 5 处文档图片相对链接少了一层目录（../figures → en/figures），目标文件存在但链接 404-ops-ras-AtomGit

Closed

[L2] fix: 5 处文档图片相对链接少了一层目录（../figures → en/figures），目标文件存在但链接 404 #132

eieieiAdd on Oct 2Closed at 16 days agoMerged fromwsnidie1/ops-ras： fix-relative-link-paths into cann/ops-ras： master

[L2] fix: 5 处文档图片相对链接少了一层目录（../figures → en/figures），目标文件存在但链接 404 #132

Closed

eieieiAdd on Oct 2Closed at 16 days ago

Merged fromwsnidie1/ops-ras fix-relative-link-pathsintocann/ops-ras master

Total: 1 files changed+5-5

Mdocs/quant_mode_introduction.md+5-5

	@@ -20,32 +20,32 @@ Quantization modes (also known as quantization granularity) refer to the use of
20		20
21	Assuming the left matrix shape is (m, k) and the right matrix shape is (k, n), where k is the reduce axis, the shape of the generated quantization parameter is (1, ).	21	Assuming the left matrix shape is (m, k) and the right matrix shape is (k, n), where k is the reduce axis, the shape of the generated quantization parameter is (1, ).
22		22
23	- ![Schematic diagram](../figures/pertensor_quantization.png)	23	+ ![Schematic diagram](en/figures/pertensor_quantization.png)
24		24
25	- Perchannel quantization (abbreviated as C quantization): The quantization target is the right matrix. Each channel uses an independent quantization parameter.	25	- Perchannel quantization (abbreviated as C quantization): The quantization target is the right matrix. Each channel uses an independent quantization parameter.
26		26
27	Assuming the right matrix shape is (k, n), where k is the reduce axis, the shape of the generated quantization parameter is (n, ).	27	Assuming the right matrix shape is (k, n), where k is the reduce axis, the shape of the generated quantization parameter is (n, ).
28		28
29	- ![Schematic diagram](../figures/perchannel_quantization.png)	29	+ ![Schematic diagram](en/figures/perchannel_quantization.png)
30		30
31	- Pertoken quantization (abbreviated as K quantization): The quantization target is the left matrix. Each token uses an independent quantization parameter.	31	- Pertoken quantization (abbreviated as K quantization): The quantization target is the left matrix. Each token uses an independent quantization parameter.
32		32
33	Assuming the left matrix shape is (m, k), where k is the reduce axis, the shape of the generated quantization parameter is (m, ).	33	Assuming the left matrix shape is (m, k), where k is the reduce axis, the shape of the generated quantization parameter is (m, ).
34		34
35	- ![Schematic diagram](../figures/pertoken_quantization.png)	35	+ ![Schematic diagram](en/figures/pertoken_quantization.png)
36		36
37	- Pergroup quantization (abbreviated as G quantization): The quantization target can be either the left matrix or the right matrix. Data is grouped on the reduce axis, and each group uses an independent quantization parameter.	37	- Pergroup quantization (abbreviated as G quantization): The quantization target can be either the left matrix or the right matrix. Data is grouped on the reduce axis, and each group uses an independent quantization parameter.
38	- Assuming the left matrix shape is (m, k), where k is the reduce axis, data is grouped on the k axis with a group size of gs, and the shape of the generated quantization parameter is (m, k/gs).	38	- Assuming the left matrix shape is (m, k), where k is the reduce axis, data is grouped on the k axis with a group size of gs, and the shape of the generated quantization parameter is (m, k/gs).
39	- Assuming the right matrix shape is (k, n), where k is the reduce axis, data is grouped on the k axis with a group size of gs, and the shape of the generated quantization parameter is (k/gs, n).	39	- Assuming the right matrix shape is (k, n), where k is the reduce axis, data is grouped on the k axis with a group size of gs, and the shape of the generated quantization parameter is (k/gs, n).
40		40
41	- ![Schematic diagram](../figures/pergroup_quantization.png)	41	+ ![Schematic diagram](en/figures/pergroup_quantization.png)
42		42
43	- Perblock quantization (abbreviated as B quantization): The quantization target can be either the left matrix or the right matrix. Data is divided into blocks on all axes, and each block uses an independent quantization parameter.	43	- Perblock quantization (abbreviated as B quantization): The quantization target can be either the left matrix or the right matrix. Data is divided into blocks on all axes, and each block uses an independent quantization parameter.
44		44
45	- Assuming the left matrix shape is (m, k), where k is the reduce axis, data is grouped on the m and k axes by (bs, bs) blocks, where bs is the block size. The shape of the generated quantization parameter is (m/bs, k/bs).	45	- Assuming the left matrix shape is (m, k), where k is the reduce axis, data is grouped on the m and k axes by (bs, bs) blocks, where bs is the block size. The shape of the generated quantization parameter is (m/bs, k/bs).
46	- Assuming the right matrix shape is (k, n), where k is the reduce axis, data is grouped on the k and n axes by (bs, bs) blocks, where bs is the block size. The shape of the generated quantization parameter is (k/bs, n/bs).	46	- Assuming the right matrix shape is (k, n), where k is the reduce axis, data is grouped on the k and n axes by (bs, bs) blocks, where bs is the block size. The shape of the generated quantization parameter is (k/bs, n/bs).
47		47
48	- ![Schematic diagram](../figures/perblock_quantization.png)	48	+ ![Schematic diagram](en/figures/perblock_quantization.png)
49		49
50	## Common Combined Quantization	50	## Common Combined Quantization
51		51