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
- Update algos.py for speculators style causal dflash config
- [Bugfix] Fix Gemma4 audio crash with variable-length batched inputs
- [ROCm][CI] Adding rocm multinode proto
- [Bug]: SpeculativeConfig silently overrides the user's explicit speculative method (model_type and path-substring auto-detection)
- [Bugfix][Spec Decode] Never silently override an explicitly configured speculative method
- [Rust Frontend] add gigachat3 tool parser
- [Bug]: GLM tool_call required + streaming causes JSON repetition
- [KVConnector] Guard lmcache_mp_connector state transition with num_external_tokens
- fix: reject routed experts capture for dense models
- [Bugfix] 'Already borrowed' by pooling tokenizer in StructuredOutputManager
- Docs
- Python not yet supported