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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel][Helion][1/N] Add Helion kernel for silu_and_mul_dynamic_per_token_quant
- [Kernel][Helion][1/N] Add Helion kernel for scaled_mm_blockwise
- Revert "[Bugfix][CPU] Remove invalid extra deps" (#43977)
- [Feature] Support DCP with FP8 KV cache in MLA decode path
- MiniMax-M2.1/M2.5/M2.7 tool-call arguments cannot safely contain raw </parameter> delimiters
- [Bug]: Eagle3 Speculative Decoding + tensor_parallel_size=2 + draft_tensor_parallel_size=2 causes NCCL timeout / collective deadlock
- [Tests] Add parallel sampling tests for AsyncLLM and LLMEngine
- [Bugfix] Pass routed_scaling_factor to FlashInfer TRTLLM MXFP4 MoE
- [RFC]: Offloading Metrics Redesign
- [Bugfix] Fix integer overflow in libtorch_stable/activation_kernels.cu pointer arithmetic
- Docs
- Python not yet supported