mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 13:52:07 +00:00
d6881c37ab
* Putting back the NCCL forced upgrade. * . * ... * Ignoring conda. * Dropping conda from the buidl system + torch 2.6 * Cache min. * Rolling back torch version. * Reverting the EETQ modification. * Fix flash attention ? * Actually stay on flash v1. * Patching flash v1. * Torch 2.6, fork of rotary, eetq updated. * Put back nccl latest (override torch). * Slightly more reproducible build and not as scary.
7 lines
373 B
Plaintext
7 lines
373 B
Plaintext
install-flashinfer:
|
|
# We need fsspec as an additional dependency, but
|
|
# `pip install flashinfer` cannot resolve it.
|
|
uv pip install fsspec sympy==1.13.1 numpy
|
|
uv pip install -U setuptools
|
|
TORCH_CUDA_ARCH_LIST="8.0;8.6;8.9;9.0+PTX" FLASHINFER_ENABLE_AOT=1 pip install git+https://github.com/flashinfer-ai/flashinfer.git@v0.2.0.post1#egg=flashinfer --no-build-isolation
|