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 supported51 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [V1][Scheduler] Add streaming prompt prefill support
- [Bugfix][Distributed] Retain shared memory handle until after barrier in in_the_same_node_as
- [Bug]: MLA decode fails on GB10 — shared memory 102400 > 101376; num_stages guard in _decode_grouped_att_m_fwd only fires for BLOCK_DMODEL >= 1024
- [Bugfix] Ignore q_scale for FlashInfer native BF16 queries
- [RFC]: Apply MoE weight transformations at disk streaming time instead of materializing raw tensor
- [Spec Decode] Verify in head dtype and drop the FP32 chunk workaround
- [CI] Fix torch-nightly Rust frontend version mismatch
- CMake: build vllm-flash-attn with ExternalProject
- [Bugfix][Spec Decode] Order input prep after the previous step's spec-decode postprocess
- [Multimodal] Set ViT DP as default mm encoder TP mode
- Docs
- Python not yet supported