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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Docs] Clarify Mistral parallel tool call workaround in tool_calling.md
- SamplingParams accepts float for int fields (max_tokens/min_tokens/logprobs), then LLM.generate() hangs on an EngineCore msgspec decode error
- [Bugfix][EPLB] Record the load window by logical expert
- [Bug]: deepseek-v4-flash-0731 repeat and Garbled characters
- [Refactor][KV Offload] Split shared offload regions into concrete classes
- [Frontend] generate: packed top-k logprobs (packed_top_k_logprobs)
- [Feature][Frontend] Add optional fastapi-guard security middleware
- [KV Cache] Size packed groups by pooled bytes per request, not layer padding
- [Bug] DFlash draft model: fp8 `ignored_layers` are not aliased to global layer indices, so excluded bf16 projections are loaded into fp8 parameters (acceptance drops from 4.3 to 1.0)
- [ROCm][KV Connector] Support sleep mode with MoRIIOConnector over RDMA
- Docs
- Python not yet supported