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
- [Question] async scheduling defaults to on for ROCm + MTP speculative decoding, while vLLM's own ROCm CI disables that combination (#32275) — was the hang root-caused, and should the default resolution encode it?
- [Feat] merge qkv into single arg for kda_attention op
- [Bug]: benchmark_moe.py quantizes weights with current_platform.fp8_dtype() but builds the quant config with a hardcoded float8_e4m3fn
- [RFC]: Native Text Watermarking Support
- [ROCm][CI] ROCM_AITER_FA MLA prefill backend never exercised in nightly CI
- [Feature] Add request-static YaRN profiles for mRoPE
- [Bug]: crashed engine leaks /dev/shm/vllm_offload_*.mmap, making every in-place container restart fail at SharedOffloadRegion init
- [Kernel] Add a FlashInfer SM90 MXFP4 x FP8 fused MoE backend
- [Model]: GLM-5.3-Flash (glm5_next): no sparse-MLA attention path on Ada (sm_89, RTX 4090)
- [ROCm][CI] Add multi-GPU test groups for nightly-log-confirmed skips (#53840)
- Docs
- Python not yet supported