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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: TurboQuant `_continuation_prefill` OOMs and kills engine at long-context prefill (~185K actual tokens)
- reasoning: fix NemotronV3 content:null when --reasoning-config is used
- [RFC]: Expose per-parameter sharding as DTensor metadata
- Chore: Fix minor doc sentence, grammar, quote errors
- feat(qwen): register Qwen3_5ForCausalLM and Qwen3_5MoeForCausalLM architectures
- [Feature]: Add ROCm support for simple offload connector
- Update quantization propagation handling in ModelOpt and NemotronH_Nano_VL
- compilation: cap cudagraph sizes for TP Marlin on Ampere
- [Performance][DSR1]: Fused RoPE+KVCache+q_concat for MLA
- [Bugfix][Ray] Fix RayExecutorV2 actor name collision with DP > 1
- Docs
- Python not yet supported