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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Track offloading allocations without load tokens
- [Cleanup][Gemma4] Remove tool_parsers/gemma4_utils.py in favor of Transformers v5 chat parsing API
- [Perf][KVConnector][Mooncake]: parallelize sub-batch KV cache loading
- [ROCm][DistInf] Enable vLLM DI CI with buildkite/slurm
- [Usage]: Serving the model opt Quantized W8A8
- [Bugfix][GB10] Fix negative CUDA graph memory estimate on unified-memory GPUs (#44740)
- [WIP][Perf] AsyncTP fusion for dynamic per-group FP8 scaled_mm + comms
- [Bug]: Implicit failure when using tiered offloading with insufficient CPU space
- [Bug]: Offloading connector possibly offloading stale KV data
- [Bug]: Tool parser returns nested object arguments as JSON strings when tool schema uses $defs/$ref
- Docs
- Python not yet supported