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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Feat: Support mixed placement of shared & router experts with EPLB synergy
- [Doc]: Eagle3 with tensor parallelism
- [Doc] Clarify tensor parallelism support for EAGLE-based draft models
- Add torch.distributed fallback for all_gatherv when PyNCCL unavailable
- fix: improve Mistral tokenizer auto-detection to check model architec…
- [Model] Support SentenceTransformers V6 reranker config
- [Bugfix]: update global_rank when adjusting rpc_rank to fix layer key error
- [Bugfix] Make executor wake_up idempotent and robust to invalid tags
- [Fix] Use torch.empty for output in attention+quant fusion
- [Bugfix] Use isinstance() instead of type() in LoRA can_replace_layer
- Docs
- Python not yet supported