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
- [Bug]: kimi-k2-thinking running 500 error
- [CI/Build] Add max_jobs docker build arg to rocm_base to prevent oom
- [Feature]: Disable logging `/metrics`
- fix: Add PIECEWISE cudagraph mode config for prefill server to avoid startup errors
- [Bug]: AttributeError: 'NoneType' object has no attribute 'use_mxfp4_w4a16'
- [Bug]: Granite Speech Illegal Memory Accesses in Parallel Vocab w/ LoRA
- [Performance]: Kimi v2 thinking Performance Uplift Plan on ROCM Platform
- [Bugfix] Add audio-overlap-chunk-second CLI arg to prevent word duplication on audio transcription
- [Bug]: Qwen3-Coder-480B-FP8 running on 8*H20,deepgemm warmup OOM
- [Feature]: rpc timeout
- Docs
- Python not yet supported