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 supported40 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- pause log
- Refactor RMSNorm vectorized launch checks
- [Bugfix] Add @register_fake for dsv3_fused_a_gemm
- [Installation]: hint: `fastsafetensors` (v0.3.2) was included because `vllm` (v0.22.1rc1.dev123+g0e2b13103.d20260603) depends on `fastsafetensors`
- [Feature]: Streaming input for VLM models
- [ROCm] Simple CPU offload is slow without hipMemcpyBatchAsync mapping
- [DO NOT MERGE][Perf][Feat] Add generic cuteDSL LL FP32 router (GEMM)
- [Feature]: AMD Zen CPU CI
- [Feature]: Add OpenTelemetry attributes input_tokens and output_tokens
- [Perf] Optimize Voxtral realtime streaming overhead
- Docs
- Python not yet supported