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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ModelRunnerV2] Support prompt embeds
- [Feature]: Support DDTree speculative decoding
- Codec: token-native binary transport for /v1/completions + /v1/chat/completions streaming
- RISC-V ILP Optimization: Add instruction-level parallelism for transcendental functions
- [Bugfix][kv_offload] Dedup gpu_block_ids in eager-mode SCO (store + load paths)
- [Bug]: NIXL disagg fails for Qwen3.5 hybrid model when prefill TP4 and decode DP8 use different physical block sizes
- [WIP] Abstract preprocess for k25
- [Feature]: DeepSeek V4 w4a4 MegaMoE support
- [Bug]: integer overflow in activation_kernels.cu
- [Bug]: integer overflow in layernorm_kernels.cu
- Docs
- Python not yet supported