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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Consolidate scale out entrypoints
- [XPU] Enable new online fp8 quantization frontend on XPU
- fix benchmarks: chat_template_kwargs ignored in spec_bench/custom_audio, causing distorted thinking-model metrics
- Gemma-4 tool call parser leaks raw tokens (<|" and "|>) into streaming response instead of parsing to standard tool_calls JSON
- Perf/wna16 batched marlin block size
- [Performance] Remove output.zero_() hotspot on the Marlin BatchedExperts path
- [KV Connector][Mooncake] Pipeline-parallel support for PD-disaggregated serving with Mooncake connector
- [Bugfix] Fix Gemma4 tool call parser using vocab key instead of decoded token string
- [Bugfix] Two independent fixes uncovered while running Quark-quantized MoE checkpoints on ROCm.
- [Bugfix] Gemma4: handle variable-length audio batches
- Docs
- Python not yet supported