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
- enable humming wNaM inference for N=[23567] M=[48]
- [Bugfix][Spec Decode] Disable dynamic speculative decoding for fixed-K proposers instead of crashing
- Bump the minor-update group across 1 directory with 146 updates
- [Refactor] Remove dead kernel code
- [Bug]: Hybrid Mamba PD-disagg under pipeline-parallel (PP>1) emits degenerate output — FullAttention region_group_ids collapse to the Mamba group under HMA
- [ROCm][CI]Fix test_concat_and_cache_mla_rope_fused on ROCm
- [Test] Add MoE dtype asserts for hidden states and logits
- [XPU] Constrain subprocess ZE_AFFINITY_MASK to local_world_size to prevent hangs, DEVICE_LOST
- [ROCm][CI] Enable modular OAI Triton MoE tests
- [RFC]: `nccl-m2n` for sharding-aware weight transfer in vLLM RL
- Docs
- Python not yet supported