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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: Suboptimal SM90 FP8 CUTLASS MoE dispatch on H20 EP8 — upstream fix proposed
- [ROCm][Perf] Fuse the GDN gated RMSNorm into out_proj at decode
- [Bugfix] Flush DeepSeek V3.1 tool arguments that do not end in a string
- [CI][macOS] Make RunAI test dependencies platform-aware
- [Model] Add Laya decision pooling
- [Perf][DSv4.1] Share the FlashMLA decode plan across KV cache groups
- [Bugfix][Spec Decode] Avoid dynamic query lengths for draft decode graphs
- [Bugfix] DeepSeek V4.1 Flash failed to stream back to the client
- [Bug]: gpt-oss (HarmonyParser): a stray 'commentary to=assistant' header is returned as a tool call named 'assistant<|channel|>analysis'
- [Bugfix][Model] Fix GLM non-mHC sequence-parallel decoder layout
- Docs
- Python not yet supported