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
- [Bug][ROCm] DSv4 with MRV2 + FULL_DECODE_ONLY has bad accuracy
- [Kernel][Quantization][XPU] Tensor-descriptor path for fused_moe_kernel_gptq_awq (int4)
- [Bug]: --mm-encoder-tp-mode data` crashes engine on multi-image requests with Qwen3.8-27B (NVFP4, TP=4, sm_120)
- [Rust Frontend] Add Hunyuan A13B reasoning parser
- [Feature]: Add torch.compile support for SiglipEmbeddingModel
- [Bug][NomicBert] Dynamic NTK corrupts RoPE cache when served length is below training length
- [ROCm][Perf] Use a stacked hipBLASLt GEMM for the bf16x3 router
- [Reasoning] Break repeating reasoning loops by forcing the reasoning end sequence
- Minimaxm3-fp4 Fuse AR+GemmaNorm
- [ROCm] Tune gfx1100 unified attention for long prefill
- Docs
- Python not yet supported