[PR #163] [MERGED] Make various updates and fixes #274

New issue

Closed

opened 2026-10-26 21:15:39 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 21:15:39 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepGEMM/pull/163
Author: @RayWang96
Created: 8/15/2025
Status: ✅ Merged
Merged: 8/15/2025
Merged by: @LyricZhao

Base: main ← Head: bf16_support

📝 Commits (1)

6439a3d Make various updates and fixes:

📊 Changes

29 files changed (+1726 additions, -96 deletions)

View changed files

📝 README.md (+1 -1)
📝 csrc/jit/compiler.hpp (+2 -2)
📝 csrc/jit/handle.hpp (+1 -1)
📝 csrc/jit/kernel_runtime.hpp (+2 -2)
📝 csrc/jit_kernels/heuristics/common.hpp (+1 -1)
📝 csrc/jit_kernels/heuristics/sm100.hpp (+2 -2)
📝 csrc/jit_kernels/heuristics/sm90.hpp (+7 -3)
📝 csrc/jit_kernels/impls/sm100_fp8_gemm_1d1d.hpp (+1 -1)
📝 csrc/jit_kernels/impls/sm100_fp8_gemm_1d2d.hpp (+1 -1)
➕ csrc/jit_kernels/impls/sm90_bf16_gemm.hpp (+229 -0)
📝 csrc/jit_kernels/impls/sm90_fp8_gemm_1d2d.hpp (+1 -1)
📝 csrc/jit_kernels/impls/smxx_layout.hpp (+56 -9)
📝 csrc/python_api.cpp (+179 -8)
📝 csrc/utils/exception.hpp (+10 -3)
📝 deep_gemm/__init__.py (+37 -9)
📝 deep_gemm/include/deep_gemm/common/scheduler.cuh (+14 -8)
📝 deep_gemm/include/deep_gemm/common/sm90_utils.cuh (+76 -0)
📝 deep_gemm/include/deep_gemm/common/utils.cuh (+18 -0)
📝 deep_gemm/include/deep_gemm/impls/sm100_bf16_gemm.cuh (+494 -1)
📝 deep_gemm/include/deep_gemm/impls/sm100_fp8_gemm_1d2d.cuh (+5 -1)

...and 9 more files

📄 Description

Add BF16 support for SM90 and SM100
Other fixes and code refactoring

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/DeepGEMM/pull/163 **Author:** [@RayWang96](https://github.com/RayWang96) **Created:** 8/15/2025 **Status:** ✅ Merged **Merged:** 8/15/2025 **Merged by:** [@LyricZhao](https://github.com/LyricZhao) **Base:** `main` ← **Head:** `bf16_support` --- ### 📝 Commits (1) - [`6439a3d`](https://github.com/deepseek-ai/DeepGEMM/commit/6439a3d7f828b6c18168f894bbf51cb4ad6c87ec) Make various updates and fixes: ### 📊 Changes **29 files changed** (+1726 additions, -96 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -1) 📝 `csrc/jit/compiler.hpp` (+2 -2) 📝 `csrc/jit/handle.hpp` (+1 -1) 📝 `csrc/jit/kernel_runtime.hpp` (+2 -2) 📝 `csrc/jit_kernels/heuristics/common.hpp` (+1 -1) 📝 `csrc/jit_kernels/heuristics/sm100.hpp` (+2 -2) 📝 `csrc/jit_kernels/heuristics/sm90.hpp` (+7 -3) 📝 `csrc/jit_kernels/impls/sm100_fp8_gemm_1d1d.hpp` (+1 -1) 📝 `csrc/jit_kernels/impls/sm100_fp8_gemm_1d2d.hpp` (+1 -1) ➕ `csrc/jit_kernels/impls/sm90_bf16_gemm.hpp` (+229 -0) 📝 `csrc/jit_kernels/impls/sm90_fp8_gemm_1d2d.hpp` (+1 -1) 📝 `csrc/jit_kernels/impls/smxx_layout.hpp` (+56 -9) 📝 `csrc/python_api.cpp` (+179 -8) 📝 `csrc/utils/exception.hpp` (+10 -3) 📝 `deep_gemm/__init__.py` (+37 -9) 📝 `deep_gemm/include/deep_gemm/common/scheduler.cuh` (+14 -8) 📝 `deep_gemm/include/deep_gemm/common/sm90_utils.cuh` (+76 -0) 📝 `deep_gemm/include/deep_gemm/common/utils.cuh` (+18 -0) 📝 `deep_gemm/include/deep_gemm/impls/sm100_bf16_gemm.cuh` (+494 -1) 📝 `deep_gemm/include/deep_gemm/impls/sm100_fp8_gemm_1d2d.cuh` (+5 -1) _...and 9 more files_ </details> ### 📄 Description - Add BF16 support for SM90 and SM100 - Other fixes and code refactoring --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 21:15:39 +00:00