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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: int8_per_token_head KV cache corrupts Gemma-4 (hybrid attention) output under load on Triton
- [Bug]: Gemma4 streaming: `content` comes back completely empty while `reasoning` holds the model's entire output when the reasoning channel is left open
- [Attention] Add FlashInfer XQA decode support on SM12x
- [Fix] Strip whitespace for VLLM_USE_MODELSCOPE env check
- [Bugfix] Terminate background stream consumers when producer exits early
- [Performance]: Modelopt quantized model goes slower in fp8 than BF16 on B200 (sm100) using vLLM 0.25.1
- [Bug]: Responses custom tools are coerced to function_call on non-Harmony Qwen routes
- [Bug][Qwen 3.5 4B][H100]: Performance of DFlash is lower than expected
- [Bugfix] Hoist $defs/definitions in Cohere parser tool schema composition
- [Bugfix][Sampling] Clear empty side on thinking-budget asymmetric SWAP
- Docs
- Python not yet supported