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
- [Bugfix][Tool Parser] GigaChat3: stop special tokens split across deltas leaking into output
- [Offloader] Prefetch weight offloading for large MoE models, plus a schedule planner
- [Core] Avoid importing optional modules in _has_module
- [Bug]: ray DP backend at --data-parallel-size 1 discards the derived DP master IP and falls back to 127.0.0.1
- fix(platform): resolve short-form GPU UUIDs in CUDA_VISIBLE_DEVICES
- fix(config): keep derived DP master IP with ray backend at dp=1
- [Docs][RL] Rewrite weight-transfer docs; standardize examples
- [Fix]: MTP speculative decoding crashes with RuntimeError on heterogeneous per-layer head_dim, fixed below and created a PR
- [Bugfix] Fall back to native sampler when FlashInfer sampling kernel fails to build
- [Observability] Add OpenTelemetry tracing to GPU-less render server endpoints
- Docs
- Python not yet supported