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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] [fusion] support ROCm aiter fusion of per tensor quant + rmsnorm
- [RFC]: Derive KV offload save sources from prefix-cache records
- [Rust Frontend] Add ERNIE 4.5 tool and reasoning parsers
- [Bug]: DeepSeek V4 buffers long string tool arguments until </parameter>
- [Metrics] Clarify vllm:inter_token_latency_seconds HELP text (per-output, not per-token)
- [Bugfix] Handle full event queue during ZMQ publisher shutdown
- [KV Connector][Observability] Add lifecycle tracing for NIXL push and pull
- [Bugfix][Quantization] Forward a2_scale in OCP MX MoE emulation
- [ROCm] Enable safe AITER MoE dispatch for Qwen3.6 on gfx12
- [Bug] Forward-pass CUDA OOM kills the whole EngineCore instead of preempting/rejecting the request
- Docs
- Python not yet supported