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
- [Model] Migrate Gemma4DSpark to AutoWeightsLoader
- [Feature] Disk-backed PLE n-gram tables (`VLLM_PLE_DISK_OFFLOAD_DIR`)
- fix(benchmarks): use platform FP8 dtype in MoE quant config
- fix: use correct Whisper prompt token
- [Bugfix][Frontend] Let the reasoning parser decide reasoning_ended when reasoning is hidden
- [RFC]: TreeWY: Tree Speculative Decoding for hybrid (GDN) models
- [Feature]: Entropy-Gated Dynamic Speculative Decoding (Dynamic k in {0, K}) via Real-Time Shannon Hysteresis
- [Bugfix] Clamp TurboQuant value range to fp16 before quantizing
- [Bugfix] Add compilation timeout for JSON schema and grammar in xgrammar
- [Bugfix][Frontend] Count reasoning tokens for the Muse-Glimmer parser
- Docs
- Python not yet supported