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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Add test for Nemotron Nano FP8 with LoRA adapters
- [Feature]: GPU Memory Snapshotting to reduce cold starts
- [Bugfix] Fix mamba cache mode null-block padding
- Fix double‑scaled linear RoPE cache for long‑context configs #33911
- [Tracking issue]: Issue Tracker for Qwen/Qwen3-VL-Embedding & Qwen/Qwen3-VL-Reranker
- Bump `lm-eval` version for Transformers v5 compatibility
- [Hybrid] Enable mamba prefix cache "align" mode with async scheduling
- [Bug]: mxfp4 (gpt-oss moe) on AMD rocm (W7900/gfx1100) breaks
- [BugFix] Fix small race condition when pausing generation for RL
- [Bugfix] Fix P2P NCCL KV transfer using external_req_id
- Docs
- Python not yet supported