intel/auto-round
View on GitHubA SOTA quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的量化工具包
- Stars
- 1.6k
- Forks
- 175
- Open beginner issues
- 0
- Indexed issues
- 78
- Avg merge
- 1d 19h
- Merged PRs (30d)
- 99
- Dominant language
- Python
- License
- Apache-2.0
- Last GitHub push
- Sep 16, 2026
- Latest indexed
- Sep 17, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- Code of conduct
- Beginner labels
- good first issue
-
intel/auto-round#2235 · 0 comments · 0 reactions · 1 assignee ·
-
enhancement
intel/auto-round#2237 · 0 comments · 0 reactions · 0 assignees ·
-
bug
intel/auto-round#2254 · 1 comment · 0 reactions · 0 assignees ·
-
enhancement
intel/auto-round#2262 · 0 comments · 0 reactions · 0 assignees ·
-
intel/auto-round#2267 · 0 comments · 0 reactions · 1 assignee ·
-
Model Support
intel/auto-round#2269 · 0 comments · 0 reactions · 1 assignee ·
-
bug
intel/auto-round#2282 · 0 comments · 0 reactions · 1 assignee ·
-
intel/auto-round#2283 · 4 comments · 0 reactions · 1 assignee ·
-
bug
intel/auto-round#2293 · 1 comment · 0 reactions · 0 assignees ·
-
enhancement
intel/auto-round#2298 · 0 comments · 0 reactions · 0 assignees ·
-
enhancement
intel/auto-round#2300 · 0 comments · 0 reactions · 0 assignees ·
-
enhancement
intel/auto-round#2307 · 0 comments · 0 reactions · 0 assignees ·
-
enhancement
intel/auto-round#2323 · 0 comments · 0 reactions · 0 assignees ·
-
[Bug]: MTP logic is unaware of Transformers' layer renaming and quantizes the entire model again Openbug
intel/auto-round#2324 · 2 comments · 0 reactions · 1 assignee ·
-
enhancement low priority
intel/auto-round#2336 · 3 comments · 0 reactions · 0 assignees ·
-
intel/auto-round#2347 · 3 comments · 0 reactions · 1 assignee ·
-
bug
intel/auto-round#2350 · 0 comments · 0 reactions · 0 assignees ·
-
bug
intel/auto-round#2369 · 0 comments · 0 reactions · 1 assignee ·
-
bug
intel/auto-round#2370 · 1 comment · 0 reactions · 1 assignee ·