vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Handle GPU/MIG UUIDs in CUDA_VISIBLE_DEVICES
- [Misc] Add unit test for merge_attn_states kernel
- [Bugfix] Reset Responses stream content index per item
- [Bugfix] Defer KV offload re-admit with pending jobs
- [Bugfix] Fix fireredlid compatibility.
- fix(generation): resolve #38425 — [Transformers v5] InternVL2
- [Bugfix] Structural-tag grammar omits reasoning prefix, crashing forced tool_choice when thinking is enabled
- [CPU] Fix mixed-batch GQA decode detection
- fix: DeepSeek-V4 tokenizer pickling error 'mlir_global_dtors' (closes #44949)
- fix(v1): resolve #28498 — [Bug][RL]: Port Conflict
- Docs
- Python not yet supported