deepseek-ai/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM.git synced 2026-11-05 00:47:26 +00:00
Code Issues 162 Projects Packages Wiki Activity

[PR #472] docs: add Simplified Chinese translation (README.zh.md) #475

New issue
Open
opened 2026-10-26 21:18:18 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-26 21:18:18 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepGEMM/pull/472
Author: @JasonYeYuhe
Created: 10/14/2026
Status: 🔄 Open

Base: main ← Head: docs/add-simplified-chinese-readme

📝 Commits (1)

  • ff6d2b2 docs: add Simplified Chinese translation (README.zh.md)

📊 Changes

2 files changed (+224 additions, -0 deletions)

View changed files

📝 README.md (+4 -0)
➕ README.zh.md (+220 -0)

📄 Description

Description

This pull request introduces a comprehensive Simplified Chinese translation (README.zh.md) for DeepGEMM, providing full native documentation access for the Chinese-speaking AI systems, CUDA optimization, and LLM developer communities.

Key Changes

  • Added README.zh.md mirroring upstream documentation 1:1:
    • Architecture overview (DeepJIT runtime compilation, Tensor Core GEMMs, CUTLASS/CuTe design inspiration)
    • Full news tracking (Ascend support, locality domains, Mega MoE, FP8/FP4 JIT, SM90/SM100 refactor)
    • Requirements & quick start (develop.sh, install.sh)
    • Detailed interface specifications:
      • Normal dense GEMMs (non-grouped) across NT, TN, NN, TT layouts
      • Grouped GEMMs (contiguous layout for training/prefilling) and K-axis grouping for MoE backward
      • Grouped GEMMs (masked layout for CUDA graph inference decoding)
      • V3.2 MQA kernels for the lightning indexer (non-paged and paged versions)
      • Mega MoE full kernel fusion and multi-process symmetric memory launch
      • Utilities reference (set_num_sms, tc_util, pdl, alignments, TMA layouts)
      • Environment variables (DG_JIT_*, DG_COMM_KERNEL_DEBUG, etc.)
    • Acknowledgements, License (MIT), and BibTeX citation
  • Added bidirectional navigation switchers (English · 简体中文) in both README.md and README.zh.md.
  • Added a volunteer maintenance note committing to long-term synchronization with upstream documentation updates.

No code files, build scripts, or C++/CUDA sources were altered.

🔄 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/472 **Author:** [@JasonYeYuhe](https://github.com/JasonYeYuhe) **Created:** 10/14/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/add-simplified-chinese-readme` --- ### 📝 Commits (1) - [`ff6d2b2`](https://github.com/deepseek-ai/DeepGEMM/commit/ff6d2b29ac102f349110e0a882e62ed6b2da21a6) docs: add Simplified Chinese translation (README.zh.md) ### 📊 Changes **2 files changed** (+224 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+4 -0) ➕ `README.zh.md` (+220 -0) </details> ### 📄 Description ## Description This pull request introduces a comprehensive Simplified Chinese translation (`README.zh.md`) for **DeepGEMM**, providing full native documentation access for the Chinese-speaking AI systems, CUDA optimization, and LLM developer communities. ### Key Changes - Added `README.zh.md` mirroring upstream documentation 1:1: - Architecture overview (DeepJIT runtime compilation, Tensor Core GEMMs, CUTLASS/CuTe design inspiration) - Full news tracking (Ascend support, locality domains, Mega MoE, FP8/FP4 JIT, SM90/SM100 refactor) - Requirements & quick start (`develop.sh`, `install.sh`) - Detailed interface specifications: - Normal dense GEMMs (non-grouped) across NT, TN, NN, TT layouts - Grouped GEMMs (contiguous layout for training/prefilling) and K-axis grouping for MoE backward - Grouped GEMMs (masked layout for CUDA graph inference decoding) - V3.2 MQA kernels for the lightning indexer (non-paged and paged versions) - Mega MoE full kernel fusion and multi-process symmetric memory launch - Utilities reference (`set_num_sms`, `tc_util`, `pdl`, alignments, TMA layouts) - Environment variables (`DG_JIT_*`, `DG_COMM_KERNEL_DEBUG`, etc.) - Acknowledgements, License (MIT), and BibTeX citation - Added bidirectional navigation switchers (`English` · `简体中文`) in both `README.md` and `README.zh.md`. - Added a volunteer maintenance note committing to long-term synchronization with upstream documentation updates. No code files, build scripts, or C++/CUDA sources were altered. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
public-sync-20261014
0930-release
nv_dev
fix-mega-moe-fence
public-release-2609
public-release-2607
public-release-2606
mega-update
public-release-260416
ko3n1g/ci/build-wheels
nv_dev_f8e8fb5
nv_dev_950d31a
nv_dev_67fc648
nv_dev_c491439
nv_dev_4ff3f54
v2.1.1.post3
v2.1.1.post2
v2.1.1.post1
v2.1.1
v2.1.0
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
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#475
No description provided.