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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [WIP][Hardware][CPU] testing branch for mlperf
- [Kernel] DeepGemm MoE : Integrate cuda moe permute/unpermute
- [Bug]: tensor parallelism inference doesn't run on Nvidia Blackwell 5070ti
- raise 400 Bad Request with detailed error message for `aiohttp.ClientError`
- [EPLB]: Add EPLB support for Grok1 [WIP]
- fix the mxfp4 packed qk weight loading issue for llama4
- [Feat] Import KV connector module dynamically for v0
- [UX] Move FlashInfer workspace cache inside of vLLM's cache (`~/.cache/vllm`)
- [Feat][KV offload][WIP] Separated process for CPU KV cache processing
- [FlashInfer] Truncate block tables for sliding window attention
- Docs
- Python not yet supported