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
- [Docs] Explain Engram host-memory exhaustion diagnostics
- [Recipes] Add Kimi-K2.6 overlay placement anchors and dynamic client model
- [FEAT][Rust Frontend] Attribute Responses output logprobs to visible text
- [Bugfix][Frontend] Follow tools/list pagination in MCP tool discovery
- fix(tool_parsers): preserve trailing content in Hermes2ProToolParser
- [Deps] Bump tensorizer to 2.12.1 for Python 3.14
- [ROCm][Attention] Support PCP and DCP on ROCM_AITER_MLA_SPARSE and mirror LM Eval PCP on MI355
- `llguidance` is an unconditional dependency and is loaded by `from vllm import LLM`; it blocks install and import on glibc < 2.31
- [Perf][MiniMax-M3.1] MiniMax-M3.1-Flash Specialized Decode: CuTe DSL Optimized GB300 (up to 1.45x)
- [Kernel][Mamba] Support Mamba2 ReplaySSM speculative decoding on the Triton backend
- Docs
- Python not yet supported