PyPI page
Home page
Author:
FlashInfer team
Summary:
FlashInfer: Kernel Library for LLM Serving
Latest version:
0.7.1
Required dependencies:
apache-tvm-ffi
|
click
|
cuda-python
|
cuda-tile
|
einops
|
nccl-extensions
|
nccl4py
|
ninja
|
numpy
|
nvidia-cudnn-frontend
|
nvidia-cutlass-dsl
|
nvidia-ml-py
|
packaging
|
requests
|
tabulate
|
torch
|
tqdm
Optional dependencies:
nvidia-cutlass-dsl
|
nvshmem4py-cu13
|
torch
Downloads last day:
106,114
Downloads last week:
761,103
Downloads last month:
2,960,391
7-day smoothing