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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KV Connector][Mooncake] Support device adapters and typed TP state views
- [Bug]: llama4_pythonic chat template quotes every tool call argument, losing argument types and breaking on strings containing a quote
- [CI][ROCm] Mirror MiniMax-M3 Model Tests on MI355
- [CI][ROCm] Add an AMD mirror for the DeepGEMM kernels step with AITER block-FP8 tests
- [CI][ROCm] Mirror LM Eval ReplaySSM on MI355
- [ROCm][Mamba] Support Mamba cache stochastic rounding on gfx950
- [Bugfix][Tool Parser] Quote string arguments in llama3.2/toolace pythonic templates
- [CI][ROCm] Mirror NixlConnector PD accuracy core on MI355
- [Frontend] Return Cohere grounding citations from derender
- [Benchmark] benchmark_moe: read GLM-5.3-Flash's MoE shape from its text config
- Docs
- Python not yet supported