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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: `kv_cache_dtype="fp8_e5m2"` silently corrupts output on Qwen-VL models (Qwen2-VL, Qwen2.5-VL) with default scaling
- [XPU] Disable CUDA graph memory estimate on XPU platform
- [Frontend] Supports resubmitting output items with missing fields in Responses API
- [KV Offload] Pass ReqContext to touch(), complete_load(), and complete_store()
- [torch.compile] typing/debug cleanups: standardise LoadConfig.compute_hash, Path-typed traced_files, richer cache_key_factors.json
- fix: zero DP padding via torch.where to prevent NaN propagation into MoE
- [WIP][Model Runner V2] Enable mamba align for spec decode
- [Bugfix] Redact URLs in OpenTelemetry spans
- [CI] Wire EAGLE3 acceptance length tests into spec_decode nightly lanes
- [Bugfix][SimpleCPUOffloadBackend] Dedup in-flight CPU offload stores across scheduler steps
- Docs
- Python not yet supported