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 supported37 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] MiniMax-M3 fp8_e5m2 KV cache on SM80 (A100/A800): admit the format Triton can read, fix the CUDA-graph KV corruption
- [Bugfix][KV Offload] Scale UniformTypeKVCacheSpecs groups by DCP
- [Core] Mix per-prompt seeds into seeded SamplingParams in the offline API
- perf: Capture FULL decode cudagraphs for spec-decode on FlashInfer native path
- [Bug]: AOT compile cache key ignores limit_mm_per_prompt, so image:0 and image:1 runs collide and crash with AttributeError: 'NoneType' object has no attribute 'size'
- Bump Flashinfer version to 0.6.16.post1
- [Bugfix] Scale KV page size for hidden states extraction with TP
- [Bugfix] Reject --renderer-num-workers > 1 with mm cache for generation models
- [Core][Spec Decode] Add lookahead-aware prefix cache hashing for EAGLE-style draft models
- [Core] Support partial layer loading natively using hf_overrides and ignore_patterns
- Docs
- Python not yet supported