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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- ON HOLD - [Core] Lazy/Delayed CUDA graph
- [Kernel] Optimize Triton Fused MoE kernel by splitting k-dim
- [Bug]: illegal memory access when there are multiple concurrent request
- [UX][Startup] Account for CUDA graphs during memory profiling
- Reinterpreting Fused MoE–LoRA as a Standard Fused MoE Kernel
- [Feature] Support Prefill Context Parallel (PCP) for GQA flashinfer
- [Feature] Auto-calculate num_redundant_experts for EPLB (#30075)
- [NIXL] Heterogeneous KV Layout and block_size - prefill NHD and nP > nD support
- [Bug]: openai_harmony.HarmonyError: unexpected tokens remaining in message header
- [Bugfix] Infinite loop when getting port with `VLLM_PORT` set
- Docs
- Python not yet supported