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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Pad unaligned N in SM12x CUTLASS blockwise FP8 GEMM
- [DeepSeek-V4] Handle 3-D packed hidden states in attention forward
- [Bug]: DeepSeekv4 flash on RTXpro6000 vllm benchmark input 8192 output 1024 encounter a err
- [Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM
- Port DeepGemm MHC Kernel to CuTeDSL
- fix: generic YaRN ignores mscale/mscale_all_dim; MistralAttention misses nested Llama 4 rope fields (fixes #48621)
- [Bugfix][NVFP4/FP8 MoE] Fix gated MoE crash on unaligned intermediate
- [Bugfix][KV-transfer] MoRIIO: per-layer READ-completion barrier in wait_for_layer_load
- [Bug]: FlashInfer CUTLASS MoE selected on fp4-less builds (CUDA toolkit < 12.8); gpt-oss dies at engine start
- [Frontend] Add diarized_json support for MOSS-Transcribe-Diarize
- Docs
- Python not yet supported