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][Scheduler] Skip lookahead allocation for running prefill chunks
- [Core][KV Cache] Priority-aware KV cache eviction for priority scheduling
- [Frontend] Add video decode cache
- [Bugfix][Reasoning] Mistral: scope streaming reasoning-end detection to current turn
- [do not land] [wip] Add Helion call-site routing + route per_token_group_fp8_quant
- [Bugfix][Docker] Add fastokens as optional pip extra and Docker build arg
- [Bug]: `vllm bench sweep serve_workload` crashes with "non-positive request rate" when max throughput < 1 req/s (integer floor/ceil of rate anchors)
- [New Model]: EuroBERT
- [ROCm] Make aiter fused-qk-rmsnorm capability probe crash-safe
- [Feature]: Support llmcompressor W8A8-FP8-Dynamic quantization for ModernBERT
- Docs
- Python not yet supported