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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Doc]: VLLM_USE_FASTOKENS=1
- [Formatting] Collapse multi-line arg lists where possible
- [deepseek_v4 / DeepGEMM] paged_mqa_logits kernel asserts on next_n=3 → num_speculative_tokens capped at 1 on Hopper
- Update FastAPI dependency to exclude fastapi-cloud-cli
- [Bugfix][DeepseekV4] Harden compress_ratio fallback for transformers >=4.57
- [Bugfix] Make openai_serving_render optional in OpenAIServingChat and OpenAIServingCompletion
- [deepseek_v4] Route top-level head.weight + embed.weight to MTP shared_head/embed_tokens
- Enable DeepSeek V4 and GLM-5.1 on SM120
- Enable FlashInfer checkpointing SSU STP no-fallback path
- [Frontend] Expose logprob_token_ids on OpenAI chat/completion endpoints
- Docs
- Python not yet supported