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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Quantization][Perf] Fuse the block Hadamard input rotation into AITER's MXFP4 activation quant
- [ROCm] Add K3 MegaMoE
- [Bug]: DS V4.1 Flash1017 outputs incorrect numbers
- [ROCm][Kernel] Add AITER W4A16 linear kernel (gemm_a16w4) for gfx942
- [Bugfix][Attention] Gracefully handle CUDA builds without FlashAttention extensions
- [Bugfix][HiSparse] Pin the shared host pool once instead of once per TP rank
- [Perf][DSv4.1] Reuse sparse indices across attention layers
- [Doc] Fix stale file paths, CLI commands, and Buildkite dependency paths
- [Bug]: Hermes tool parser streaming silently drops all content after a stray <tool_call> marker in prose
- [XPU][CI] Test intel_gpu_k8s
- Docs
- Python not yet supported