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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][LoRA] Map lm_head LoRA to batch tokens for prompt logprobs (…
- [MoE] Stage UVA-offloaded expert weights in VRAM for large steps
- [Bugfix][Spec Decode] Keep data_parallel_index in DFlash/DSpark draft configs
- [Bugfix][Qwen4Exp] Fix PLE layerwise reload with CPU offload and TP
- [Bugfix][MoE] Keep per-expert gate/up halves separate under stacked mappers
- [Bugfix][Tokenizer] Honor truncation_side in MistralTokenizer.encode
- [Feature][Elastic EP] Correlate external scaling operations
- [RFC / Research Showcase] SPICY-KV: 28.6x–50x Pre-RoPE Algebraic Multigrid KV Compression + 4-Byte Subgrid Variance Calibration (91.7%–100% RULER Recall on DeepSeek-R1 7B & 1.5B)
- [Perf] Add VLLM_GC_THRESHOLDS to set GC thresholds after the heap freeze
- [ROCm][Quantization] Add AITER hipBLASLt MXFP8 linear kernel
- Docs
- Python not yet supported