[Fix] Fix Inference Example, Tests, and Requirements (#5688)

* clean requirements

* modify example inference struct

* add test ci scripts

* mark test_infer as submodule

* rm deprecated cls & deps

* import of HAS_FLASH_ATTN

* prune inference tests to be run

* prune triton kernel tests

* increment pytest timeout mins

* revert import path in openmoe
This commit is contained in:
Yuanheng Zhao
2024-05-08 11:30:15 +08:00
committed by GitHub
parent f9afe0addd
commit 55cc7f3df7
23 changed files with 46 additions and 328 deletions

View File

@@ -91,7 +91,7 @@ jobs:
container:
image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
options: --gpus all --rm -v /dev/shm -v /data/scratch/llama-tiny:/data/scratch/llama-tiny
timeout-minutes: 60
timeout-minutes: 75
defaults:
run:
shell: bash