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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: sample_tokens RPC timeout with GLM-5.2-FP8 + DSpark speculative decoding, TP=8 across 2 nodes (Blackwell GB200)
- [RFC]: Context-length-aware speculative token scheduling — extending num_speculative_tokens_per_batch_size with a context-length axis
- `NixlPushMode` Roadmap - Reliability Issue Inventory
- [Tests] Cover Nemotron V3 required XML tool parsing
- [Feature]: Support fast weight updates from disk
- [wip] add context parallelism for minimax m3 indexer
- transformers backend: per_token_group_quant_8bit not implemented for Float8_e4m3fn (FP8 MoE models)
- [Bugfix][DBO] Include ubatch id in attention metadata cache key
- Expose public get_layer_params(config) helper for Gemma4 per-layer attention/FFN params
- [Bug]: `minimax_m3` reasoning parser splits structured-output JSON at a `<mm:think>` the model wrote as content
- Docs
- Python not yet supported