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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] fixes shared expert forwarding in fused_moe.
- Add SamplingParams.shallow_copy to only clone mutable fields
- [Performance]: Fully Async Spec-Decoding | Make `seq_lens_cpu` in CommonAttentionMetadata optional
- [Bug]: cpu-offload-gb crashes with "CPU tensor must be pinned"
- Prototyping single batch overlapping for Deepseek EP
- [RFC]: Support Dynamic Context Parallelism
- [Bug]: triton 3.5 for gpt-oss fails on sm11.0a cu130
- [Refactor] Split up compressed_tensors_moe.py into separate files per method
- Add OpenVLA model support
- Fix missing as_list() conversion in streaming chat completion
- Docs
- Python not yet supported