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 supported52 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Add Holo2 reasoning parser
- [XPU] Work around Battlemage oneCCL IPC handle cache device-loss failures
- [Feature] Enable AITER MXFP4 MoE on gfx942 and optimize tile configurations for MI325X Target Kimi K3 running on MI325X
- Remove attention layer name from unified_kv_cache_update for torch.compile
- Fix weight loading I/O contention and add FlashInfer autotune logging
- fix(model): ensure cpu tensor contiguity during Llama4 ModelOpt weight loading
- Fix OverflowError in prompt_logprobs when external KV pre-fills prompt
- Add external metrics providers for stat logger plugins
- [Bug]: sm_120 + local CUDA toolkit < 12.9: FlashInfer JIT failures kill engine init in three default paths (sampler, fused-MoE, FP8 KV) instead of falling back
- [Bugfix][NIXL] Preserve block geometry for packed MLA caches
- Docs
- Python not yet supported