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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][MiniMax-M3] gfx942 MXFP4 indexer: fixes, fused decode, fast prefill
- [ROCm][MiniMax-M3] Serve --kv-cache-dtype mxfp4 on gfx942
- [Perf] Add opt-in FlashInfer multimodal encoder autotuning
- [watermarking] Support block verification with dual_key_gumbel watermarking
- [Perf] [NVIDIA] attention: Improve the DSA prefill kernel with LiteTopK (FP8, GLM-5.x / DeepSeek) on SM100
- [ROCm][MORI IO]Moriio hybrid load failure
- [Bug]: DeepSeek-V4.1 with DSpark adaptive verification crashes at startup on MI355X (TP8) with a GPU memory access fault
- [Kernel][Perf] Add H100 BF16 tuned configs for Qwen2.5-7B to the batch-invariant matmul table
- [Perf][MiniMax-M3] Two-shot fused MoE finalize + all-reduce + norm + MXFP8 up to 512 tokens
- [Perf] Bypass the dispatcher for all vLLM custom ops in eager mode
- Docs
- Python not yet supported