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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel][Triton] Tune unified_attention for head_dim>=512 (Gemma 4 global attention)
- [Performance]: MTP seems to be very slow
- Enable B12x backend for non-gated MoEs (like Nemotron)
- [Kernel] Add native CUDA fused RoPE + KV cache write op, opt-in for flash_attn
- [Bugfix] FusedMoE: coerce shape-(1,) per-tensor scales to 0-D scalar …
- [Core] AsyncLLM.truncate_session: per-session KV cache truncation API
- [Misc] Tolerate malformed Harmony streams.
- [Feature]: Support streaming output for tool_calls arguments
- [B12x][NVFP4] Add W4A16 support to FlashInfer SM12x MoE wrapper
- [WIP] Add FlashInfer NVFP4 GEMM + reduce-scatter fusion
- Docs
- Python not yet supported