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 supported50 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Quantization] Gate FP8 Marlin on supported weight group shapes
- [ROCm] Enable Kimi-K3 for Gfx1250
- [Feature][Spec Decode]: host-context hook between draft proposal and verify for out-of-graph per-layer caches
- [Build] Install vllm-rs as a native command
- [Bugfix] Retain one alignment block below sliding-window replay boundaries so a same-turn extension still hits the prefix cache
- [Docs] Document NIXL KV connector metrics aggregation semantics
- [Bugfix] Plain MTP must not trigger the all-groups eagle-group fallback (it zeroes all prefix-cache insertions)
- [Perf][GLM-5.3-Flash] Batch paired KDA gate projections (f_b_proj/g_b_proj) into one bmm
- [Bugfix] Scope the nested-RoPE validator patch to the allowlisted model types
- [Bugfix][ROCm] Auto-enable fp32 weights for the gfx950 router GEMM in GateLinear
- Docs
- Python not yet supported