Skip to content

Pull requests: deepseek-ai/DeepSeek-V3

New pull request New
70 Open 140 Closed
70 Open 140 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix(inference): preserve index metadata when converting fp8 to bf16
#1597 opened Aug 23, 2026 by loulanyue Loading…
1
Add inference setup tool
#1596 opened Aug 21, 2026 by Kolgrim33 Loading…
1
Improve README docs and harden inference/generate.py validation & cleanup
#1593 opened Aug 20, 2026 by Shyboy0499 Loading…
1
fix: validate generation temperature
#1589 opened Aug 18, 2026 by ryanL1100 Loading…
1
fix: validate inference and conversion edge cases
#1586 opened Aug 17, 2026 by ryanL1100 Loading…
1
feat: add inference requirements checker script
#1584 opened Aug 16, 2026 by Kolgrim33 Loading…
3
docs: update Twitter link to X in README
#1583 opened Aug 16, 2026 by Kolgrim33 Loading…
1
docs: fix broken TensorRT-LLM example link in README
#1582 opened Aug 16, 2026 by Kolgrim33 Loading…
1
docs: add deployment compatibility table and fix broken links in README
#1545 opened Aug 5, 2026 by usaihack Loading…
3
feat(inference): MTP speculative decoding with cache-aware mid-decode mask fix
#1536 opened Jul 30, 2026 by n-dlms Loading…
5
fix(inference): strip whitespace from generate.py CLI paths
#1511 opened Jul 24, 2026 by Charmve Loading…
1
feat(model): add ZazorLayer for hierarchical context memory
#1485 opened Jul 9, 2026 by AlexShchuka Loading…
24
feat: add mobile-compatible requirements (CPU-only)
#1442 opened Jun 20, 2026 by Bakomebandias Loading…
5
给github汉化
#1357 opened May 25, 2026 by whzzlsyz Loading…
1
Exercise: Add a learning comment
#1333 opened May 18, 2026 by Bryamtf Loading…
feat: add on-device persistent memory module
#1182 opened Mar 31, 2026 by zhaog100 Loading…
fix: add repetition penalty to mitigate multi-turn repetition (fixes #1125)
#1129 opened Mar 1, 2026 by modimihir07 Loading…
1
1
fix: use OrderedDict for proper LRU cache eviction in fp8_cast_bf16.py
#1128 opened Mar 1, 2026 by modimihir07 Loading…
Add Multi-Token Prediction (MTP) support for speculative decoding
#1122 opened Feb 24, 2026 by dcol91863 Loading…
docs: fix grammar in README
#1114 opened Feb 16, 2026 by csmit195 Loading…
Update stale.yml with permissions and action version
#1100 opened Feb 2, 2026 by Alb4don Loading…
fix: fix triton kernel tiling and fp8_gemm swizzle
#1098 opened Jan 29, 2026 by JackeyLove1 Loading…
feat(inference): Add streaming support imports for high-performance L…
#1080 opened Jan 13, 2026 by sanjay-aravindh Loading…
1
Enhance token generation with top-p sampling
#1079 opened Jan 13, 2026 by esball1 Loading…
Create devcontainer.json
#1075 opened Jan 4, 2026 by Tanker187 Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.