| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 14 天前 | ||
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
refactor(modeling): Restructure modeling/ to match TileGym layout Co-authored-by: u010986451<suntao37@huawei.com> # message auto-generated for no-merge-commit merge: !12 merge refactor/modeling-restructure into master refactor(modeling): Restructure modeling/ to match TileGym layout Created-by: u010986451 Commit-by: u010986451 Merged-by: cann-robot Description: Reorganize the modeling/ directory to follow the TileGym pattern with a unified transformers/ entry point containing infer.py, benchmark scripts, sample inputs, Dockerfile, and README. Changes: - Create src/pypto_gym/transformers/ with Qwen3-1.7B model definitions and PyPTO kernel adapters (moved from modeling/qwen3_1_7b/core/ and modeling/qwen3_1_7b/qwen3_pto_kernels/) - Create modeling/transformers/ with unified infer.py (supports --use_pypto, benchmark mode, per-token step timing) - Add bench_qwen3_1_7b.sh for PyTorch baseline vs PyPTO comparison - Add sample_inputs/, Dockerfile, build_docker.sh, README.md - Remove old modeling/qwen3_1_7b/ directory See merge request: cann/pypto-gym!12 | 2 个月前 | |
fix(Operator):Adjust pypto tensor directory Co-authored-by: huangyuqian<huangyuqian2@huawei.com> # message auto-generated for no-merge-commit merge: !321 merge master into master fix(Operator):Adjust pypto tensor directory Created-by: huangyuqian Commit-by: huangyuqian Merged-by: cann-robot Description: ## 变更描述 / Description <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [ ] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/pypto-gym!321 | 11 天前 | |
| 14 天前 | ||
docs: add HF download and explicit runtime patch flow Co-authored-by: leedongkun30-arch<lee.dongkun30@gmail.com> # message auto-generated for no-merge-commit merge: !255 merge feature/hf-download-runtime-patch-244 into master docs: add HF download and explicit runtime patch flow Created-by: leedongkun30-arch Commit-by: leedongkun30-arch Merged-by: cann-robot Description: ## Summary - add a generic HuggingFace snapshot download script for model-card IDs - add a generic runtime patch overlay script for local model snapshots - document the shared flow in the root README and the Gemma4, LLaDA2, MiniMax M2.7 model READMEs ## Scope - rebased directly on master - diff: root README + three model READMEs + the two shared scripts, plus the additions below ## Verification - python3 -m py_compile modeling/transformers/download_hf_model.py modeling/transformers/runtime_patch.py - git diff --check upstream/master..HEAD - download_hf_model.py verified with hf-internal-testing/tiny-random-gpt2 - runtime_patch.py verified for preset and custom overlay flows ## Also in this PR (rebased + squashed onto master) - ** .agents/skills/hf-npu-e2e-workflow** — orchestration workflow that pipelines the shared scripts into an HF → NPU E2E run: download_hf_model.py → runtime_patch.py → run → measure (eager / NPUGraph). It owns the net-new measurement layer — bench_npu.py, npu_capture.py, references/npu-run-and-measure.md (regimes prefill/decode, the 3-arm definition, the **NPUGraph capture gotcha table**: SDPA side-stream → attn_implementation="eager", mask/rotary host syncs → prebuilt mask + cached cos/sin, MoE argsort → static route, grouped_gemm dynamic shape → fix the shape). It invokes pypto-fused-op-integration only when a fused kernel is actually needed, and does **not** duplicate HF onboarding or the PyPTO USE_PTO_<OP> switch / sys.modules injection (those stay in pypto-fused-op-integration). - **pypto-fused-op-integration is NOT edited.** Its stale onboarding (raw snapshot_download, manual fix_imports.py + auto_map) and its env-specific torch==2.7.1 pin are corrected as **override notes inside hf-npu-e2e-workflow's SKILL.md** (step 5): read that skill for the fusion methodology, but use this PR's download_hf_model.py / runtime_patch.py for onboarding and match torch/torch_npu to the box's CANN. The shared skill itself stays untouched. - Rebased onto current master and squashed to a single commit. See merge request: cann/pypto-gym!255 | 15 天前 | |
| 14 天前 | ||
docs: add HF download and explicit runtime patch flow Co-authored-by: leedongkun30-arch<lee.dongkun30@gmail.com> # message auto-generated for no-merge-commit merge: !255 merge feature/hf-download-runtime-patch-244 into master docs: add HF download and explicit runtime patch flow Created-by: leedongkun30-arch Commit-by: leedongkun30-arch Merged-by: cann-robot Description: ## Summary - add a generic HuggingFace snapshot download script for model-card IDs - add a generic runtime patch overlay script for local model snapshots - document the shared flow in the root README and the Gemma4, LLaDA2, MiniMax M2.7 model READMEs ## Scope - rebased directly on master - diff: root README + three model READMEs + the two shared scripts, plus the additions below ## Verification - python3 -m py_compile modeling/transformers/download_hf_model.py modeling/transformers/runtime_patch.py - git diff --check upstream/master..HEAD - download_hf_model.py verified with hf-internal-testing/tiny-random-gpt2 - runtime_patch.py verified for preset and custom overlay flows ## Also in this PR (rebased + squashed onto master) - ** .agents/skills/hf-npu-e2e-workflow** — orchestration workflow that pipelines the shared scripts into an HF → NPU E2E run: download_hf_model.py → runtime_patch.py → run → measure (eager / NPUGraph). It owns the net-new measurement layer — bench_npu.py, npu_capture.py, references/npu-run-and-measure.md (regimes prefill/decode, the 3-arm definition, the **NPUGraph capture gotcha table**: SDPA side-stream → attn_implementation="eager", mask/rotary host syncs → prebuilt mask + cached cos/sin, MoE argsort → static route, grouped_gemm dynamic shape → fix the shape). It invokes pypto-fused-op-integration only when a fused kernel is actually needed, and does **not** duplicate HF onboarding or the PyPTO USE_PTO_<OP> switch / sys.modules injection (those stay in pypto-fused-op-integration). - **pypto-fused-op-integration is NOT edited.** Its stale onboarding (raw snapshot_download, manual fix_imports.py + auto_map) and its env-specific torch==2.7.1 pin are corrected as **override notes inside hf-npu-e2e-workflow's SKILL.md** (step 5): read that skill for the fusion methodology, but use this PR's download_hf_model.py / runtime_patch.py for onboarding and match torch/torch_npu to the box's CANN. The shared skill itself stays untouched. - Rebased onto current master and squashed to a single commit. See merge request: cann/pypto-gym!255 | 15 天前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 14 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 11 天前 | ||
| 2 个月前 | ||
| 11 天前 | ||
| 14 天前 | ||
| 15 天前 | ||
| 14 天前 | ||
| 15 天前 |