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 supported44 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- improve dynamic_per_token_scaled_fp8_quant_kernel_strided kernel
- [P/D][Mooncake] Add cross-layer KV cache support to MooncakeConnector
- fix(kv-cache): allow TurboQuant on hybrid models
- [WIP]Support DeepSeek V4 flash on SM120 with Triton fallback
- [NIXL][Bugfix] Fix block indexing in KV cache transfer for blocks-first layouts
- [Bug]: vLLM v1 with prefix caching: first request differs from subsequent identical requests at temperature=0
- [Installation]: ERROR: Failed building wheel for vllm
- [Bugfix] Skip flashinfer-rope variant in QK norm+RoPE fusion
- [Bug]: RuntimeError: flashinfer_fp8_blockscale_gemm fails on H100 NVL MIG 3g.47gb with Qwen3.6-35B-A3B-FP8
- [Bug]: Deepseek-V4-Flash failed to load on 8*L20
- Docs
- Python not yet supported