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 supported43 Subscribers
View all SubscribersAdd 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
- [torch.compile] typing/debug cleanups: standardise LoadConfig.compute_hash, Path-typed traced_files, richer cache_key_factors.json
- [Bugfix] Redact URLs in OpenTelemetry spans
- [CI] Wire EAGLE3 acceptance length tests into spec_decode nightly lanes
- [Bugfix][DeepSeek V4] Enable cross-node TP=16 FP8 serving
- Migrate gpt-oss-20b MoE backend selection from env var to model kwarg
- Fix Dynamic NTK RoPE scaling formula
- [Bug]: v0.20 latency and throughput regression on MoE models
- Fix Granite Speech audio placeholder sizing
- [Benchmark] add std_latency to bench latency output
- Docs
- Python not yet supported