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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Frontend] Preserve Whisper text without timestamp tokens
- \[Quantization\] Add support for modelopt IQ2\_XS, IQ2\_XXS, and Q8\_0 checkpoints via b12x
- [Feature] Enable triton autotuning for config reliant kernels
- [Bugfix][Attention] Keep FlashInfer's plan() staging buffer pageable
- [Feature]: Route FlashInfer sparse-MLA decode autotune through the PP-aware tuning group and cache
- [Bugfix][Kernel] Bump DeepGEMM pin for SM107 JIT compatibility
- [Bugfix][Frontend] Don't crash beam search on an extreme length_penalty
- [Bugfix][Core] Accept needs_kv_cache_zeroing in SinkFullAttentionManager
- [Perf][Kernel] Flat-grid silu_and_mul_quant: fix dead vector loop, fp32 fast-math chain
- [Bugfix][Quantization] Set orig_dtype in ModelOpt FP8 channel/block schemes
- Docs
- Python not yet supported