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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix P2pNcclConnector NCCL send/recv key mismatch in disaggregated prefill XpYd
- Fixed whisper CPU test that does not spawn properly.
- TRITION_ATTN backend support int8 kvcache dtype
- [KV Connector] Support using FlexKV as KV Cache Offloading option.
- [Multimodal] Expose `mm_processor_kwargs` for `DummyInputsBuilder`
- [Refactor] Move FusedMoE hidden_size roundup to quant_method
- kv connector: Add mooncake store connector
- [ModelBash][DSV3] Add TRTLLM DSV3 Router GEMM kernel (6% B1 Speedup)
- [Bug]: MLP Speculator AttributeError: 'MLPSpeculatorConfig' object has no attribute 'num_attention_heads'
- [Fix Bug]`num_active_loras` always equals to zero
- Docs
- Python not yet supported