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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- DeepSeek-V4-Flash-0731: KV cache holds only 150K tokens in 7.7 GiB (56 bytes/token), max_model_len capped at ~121344 on H20 TP=2
- [MyPy][2/N] Fix mypy errors in small tests/ dirs
- [Config] Improve speculative scheduling budget diagnostics
- [Bugfix] Encode special tokens in HF processors for transformers-native mistral-common tokenizers
- [Bugfix][Parser] Surface unterminated reasoning as content for deepseek_v4 (fixes #48645)
- [PD][NixlPush][Bugfix] Notify D of NIXL writes that failed to post so it stops waiting
- [Bugfix][Kimi-K3] Cover missing AttnRes warmup profiles
- [Bug]: CUDA graph memory profiler charges an mnbt-linear profiling transient as "graph memory" → KV cache pool −18–24% on hybrid GDN models since v0.26.0 (the real FULL graphs cost ~24 MiB each)
- [Frontend][Voxtral] Add opt-in segment timestamps to /v1/realtime
- [Feature][Gemma4]: Allow configuring max_soft_tokens for video frames
- Docs
- Python not yet supported