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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Remediate vllm-openai dependency vulnerability findings
- [ROCm][NVFP4] flydsl NVFP4 MOE kernel for gfx950/gfx942 (MI355/350/325/300)
- [Performance]: benchmark speed & precision of rust preproc vs pytorch
- [Bug] ~17.5s engine-wide stall on large-to-small request shape transitions (NVFP4/b12x, GDN CuteDSL prefill kernel)
- [Perf] Keep H2D transfers dense in fused-MoE weight loading
- Revert "Support nvfp4 kv with kv-cache-dtype-skip-layers sliding_window" (#42890)
- [Bug]: wrong cutlass Arch import
- [Bugfix] Treat tool parameter schemas without a type as allowing any type
- [Kernel] Add opt-in cuda cache update for flash_attn_diffkv
- DCP + split-q for speculative decoding support
- Docs
- Python not yet supported