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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [bug fix] disable memory pool to release unused `bf16` weights
- [Feat] support fp8 quantization in update weights
- [Bug]: Streaming response remains blocked until complete output is generated with gpt-oss-120B model on A100 GPU
- [Bug]: Make Whisper model compatible with cuda graphs
- [Bugfix] Qwen3-next generate ! always
- [GPT-OSS] Save `extra_weight_attrs` and use at `load_weights` time for Marlin kernel
- [Usage]: How to change the video sample fps with Qwen3-VL?
- [Bug]: RunAI model streamer breaks in 0.11
- [ROCM] Add sinks argument to AiterFlashAttentionImpl
- [Bug]: (EngineCore_DP0 pid=77352) INFO 10-22 09:43:49 [shm_broadcast.py:466] No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-consuming work (e.g. compilation).
- Docs
- Python not yet supported