[PR #188] [CLOSED] disable persistent kernel #283

New issue

Closed

opened 2026-10-26 21:15:46 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 21:15:46 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepGEMM/pull/188
Author: @HIT-cwh
Created: 9/10/2025
Status: ❌ Closed

Base: main ← Head: cwh/disable_persistent_kernel

📝 Commits (10+)

dd15f75 spelling: README.md
644ac12 Merge pull request #3 from acheong08/patch-1
298824c doc: Use permanent link
d440f51 Merge pull request #13 from ZeppLu/patch-1
54a9a97 fix: prevent expected_m from exceeding m in test_core
3dd2877 fix typo
a4cf152 Update README.md
5755d72 setup.py: fix wheel building
4cfc7a0 Merge pull request #16 from AcraeaTerpsicore/patch-1
94e69a8 Fix python -O mode issues

📊 Changes

29 files changed (+2655 additions, -293 deletions)

View changed files

📝 .gitignore (+4 -0)
📝 README.md (+23 -175)
📝 adaptive_gemm/__init__.py (+4 -2)
📝 adaptive_gemm/include/adaptive_gemm/fp8_gemm.cuh (+19 -14)
➕ adaptive_gemm/include/adaptive_gemm/fp8_gemm_dw.cuh (+619 -0)
➕ adaptive_gemm/include/adaptive_gemm/fp8_gemm_varlen_groupM.cuh (+553 -0)
📝 adaptive_gemm/include/adaptive_gemm/mma_utils.cuh (+2 -2)
📝 adaptive_gemm/include/adaptive_gemm/scheduler.cuh (+5 -5)
➕ adaptive_gemm/include/adaptive_gemm/scheduler_varlen_groupM.cuh (+138 -0)
📝 adaptive_gemm/include/adaptive_gemm/tma_utils.cuh (+2 -2)
📝 adaptive_gemm/include/adaptive_gemm/utils.cuh (+1 -1)
📝 adaptive_gemm/jit/__init__.py (+0 -0)
📝 adaptive_gemm/jit/compiler.py (+6 -5)
📝 adaptive_gemm/jit/interleave_ffma.py (+5 -6)
📝 adaptive_gemm/jit/runtime.py (+0 -0)
📝 adaptive_gemm/jit/template.py (+30 -10)
📝 adaptive_gemm/jit_kernels/__init__.py (+5 -1)
📝 adaptive_gemm/jit_kernels/gemm.py (+33 -16)
➕ adaptive_gemm/jit_kernels/k_grouped_gemm_dw.py (+433 -0)
📝 adaptive_gemm/jit_kernels/m_grouped_gemm.py (+10 -6)

...and 9 more files

📄 Description

No description provided

_{🔄 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/188 **Author:** [@HIT-cwh](https://github.com/HIT-cwh) **Created:** 9/10/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `cwh/disable_persistent_kernel` --- ### 📝 Commits (10+) - [`dd15f75`](https://github.com/deepseek-ai/DeepGEMM/commit/dd15f75bc8689fcc1ce939380d6f35f9ef11f344) spelling: README.md - [`644ac12`](https://github.com/deepseek-ai/DeepGEMM/commit/644ac1294d9fb4ae2f4c6e7d432ca37e19b9cfde) Merge pull request #3 from acheong08/patch-1 - [`298824c`](https://github.com/deepseek-ai/DeepGEMM/commit/298824c12471d804077df081cd349f024623db51) doc: Use permanent link - [`d440f51`](https://github.com/deepseek-ai/DeepGEMM/commit/d440f510124660eea6d8ec20da7957223b34b883) Merge pull request #13 from ZeppLu/patch-1 - [`54a9a97`](https://github.com/deepseek-ai/DeepGEMM/commit/54a9a971488a777ad3bed75ca4843618f710329b) fix: prevent expected_m from exceeding m in test_core - [`3dd2877`](https://github.com/deepseek-ai/DeepGEMM/commit/3dd2877b62ee7d202a32255a932f3887b744d19a) fix typo - [`a4cf152`](https://github.com/deepseek-ai/DeepGEMM/commit/a4cf152876fe36bd325817d040517b0e067826b4) Update README.md - [`5755d72`](https://github.com/deepseek-ai/DeepGEMM/commit/5755d725ff1a683783fd370ccc49285f8ad769ff) setup.py: fix wheel building - [`4cfc7a0`](https://github.com/deepseek-ai/DeepGEMM/commit/4cfc7a0dd6c2202a009d6f9e9ccc2a46c4d96087) Merge pull request #16 from AcraeaTerpsicore/patch-1 - [`94e69a8`](https://github.com/deepseek-ai/DeepGEMM/commit/94e69a8afea2ad112fa24c39c489c047e1dd11a8) Fix `python -O` mode issues ### 📊 Changes **29 files changed** (+2655 additions, -293 deletions) <details> <summary>View changed files</summary> 📝 `.gitignore` (+4 -0) 📝 `README.md` (+23 -175) 📝 `adaptive_gemm/__init__.py` (+4 -2) 📝 `adaptive_gemm/include/adaptive_gemm/fp8_gemm.cuh` (+19 -14) ➕ `adaptive_gemm/include/adaptive_gemm/fp8_gemm_dw.cuh` (+619 -0) ➕ `adaptive_gemm/include/adaptive_gemm/fp8_gemm_varlen_groupM.cuh` (+553 -0) 📝 `adaptive_gemm/include/adaptive_gemm/mma_utils.cuh` (+2 -2) 📝 `adaptive_gemm/include/adaptive_gemm/scheduler.cuh` (+5 -5) ➕ `adaptive_gemm/include/adaptive_gemm/scheduler_varlen_groupM.cuh` (+138 -0) 📝 `adaptive_gemm/include/adaptive_gemm/tma_utils.cuh` (+2 -2) 📝 `adaptive_gemm/include/adaptive_gemm/utils.cuh` (+1 -1) 📝 `adaptive_gemm/jit/__init__.py` (+0 -0) 📝 `adaptive_gemm/jit/compiler.py` (+6 -5) 📝 `adaptive_gemm/jit/interleave_ffma.py` (+5 -6) 📝 `adaptive_gemm/jit/runtime.py` (+0 -0) 📝 `adaptive_gemm/jit/template.py` (+30 -10) 📝 `adaptive_gemm/jit_kernels/__init__.py` (+5 -1) 📝 `adaptive_gemm/jit_kernels/gemm.py` (+33 -16) ➕ `adaptive_gemm/jit_kernels/k_grouped_gemm_dw.py` (+433 -0) 📝 `adaptive_gemm/jit_kernels/m_grouped_gemm.py` (+10 -6) _...and 9 more files_ </details> ### 📄 Description _No description provided_ --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 21:15:46 +00:00

closed this issue
added the
pull-request
label

No labels

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

deepseek-ai/DeepGEMM#283

No description provided.

Rows
Columns