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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Unify the kernel used in flash attention backend
- [Bug]: benchmark_serving.py cannot calculate Median TTFT correctly
- Create guided_decoding.md
- [Kernel] Support Microsoft Runtime Kernel Lib for our Low Precision Computation
- [Feature][Hardware][AMD] Enable Scaled FP8 GEMM on ROCm
- Concurrent timeout
- [New Model]: facebook/seamless-m4t-v2-large
- [Bug]: Producer process has been terminated before all shared CUDA tensors released (v 0.5.0 post1, v 0.4.3)
- [Bug]: When I inference with a 1b model, tp2 latency is greater than tp1
- [Bug]: identical branches in csrc/quantization/marlin/sparse/marlin_24_cuda_kernel.cu
- Docs
- Python not yet supported