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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix Aria garbage output at TP>1: shared experts double all-reduce
- [Perf] Split-reduction batch-invariant log_softmax for small-batch decode
- [Bug]: GLM-4.1V fails to start at tensor-parallel size 32 — vision tower head-count mismatch
- [Usage]: DSpark much slower than no-spec on single B300 (DeepSeek-V4-Flash) — config check, or not effective on a saturated batch yet?
- [Bugfix][ROCm] Fix ROCM_AITER_FA & ROCM_AITER_UNIFIED_ATTN QK-Norm+RoPE+KVCache fusion for the packed KV-cache [BLOCKS, HEADS, BLOCK_SIZE, 2*HEAD_DIM] layout
- [ROCm][CI] Add More AITER quantization/MoE kernel tests
- [Bugfix] Aria: set reduce_results=False on shared_experts to fix TP>1
- [Bug]: Poolside Laguna-S-2.1 poolside_v1 reasoning parser falls back to IdentityReasoningParser and fails auto initialization
- [ModelOpt] Redesign the LinearMethod classes using the generic QuantKey-driven method
- [WIP][Model Runner V2][Spec Decode] Enable rejection sampling with draft logits by default, capped to draft_logits_buffer_gb
- Docs
- Python not yet supported