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
- [Docs/Robustness] NIXL connector: the block_len_per_layer == seen_base_addresses assert is load-bearing for hybrid-Mamba descriptor IDs
- EPD (EC connector) Tracker
- [Bugfix][Frontend] Responses streaming: tool-call argument tail interleaved with reasoning/content aborts SSE stream (nameless ResponseFunctionToolCallItem)
- [XPU][INC] Fix RuntimeError when loading INT4 checkpoints with symmetric (empty-qzeros) layers
- [bot] Enable Gemma4 E4B (google/gemma-4-E4B-it-qat-w4a16-ct) on Intel XPU with mixed attention backends
- [Bug]: AssertionError: n_physical_experts=256 must be divisible by ep_size=3. Adjust num_redundant_experts.
- fix(missing_documentation): Class `SamplingType` in vllm/sampling_params.py has no docst
- fix(missing_documentation): Class `StructuredOutputsParams` in vllm/sampling_params.py h
- [Bugfix][Responses] Route browser streams to web search events
- [Bugfix] Initialize FP8 partition metadata for ParallelLMHead
- Docs
- Python not yet supported