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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [KVConnector][LMCache] Enable Support for cross-layer Layout
- [Metrics] Add prefix cache state metrics for KV cache monitoring
- [Performance]: Quantized Model Inference
- [Usage]: TorchDispatchMode does not work for vllm
- [Bug]: RuntimeError: CUDA error: no kernel image is available for execution on the device with nvidia v100
- [Model]Add DebertaV2ForSequenceClassification Model Support
- [RFC]: vLLM-compile (minus cudagraphs) warm-start time should be close to zero
- [Misc] Support MMMU accuracy benchmark
- [RFC]: Support Layer-Specific KV-Cache Dtype & Layout in V1 Engine for Hybrid Models
- [Bug]: default_weight_loader receives unexpected `weight_name` kwarg in GPT-OSS load_weights
- Docs
- Python not yet supported