[ROCm][CI] Prep Tests For Change To ROCM_ATTN As New Default Backend On ROCm (#36025)

Signed-off-by: Micah Williamson <micah.williamson@amd.com>
This commit is contained in:
Micah Williamson
2026-03-09 13:27:55 -05:00
committed by GitHub
parent 3fd03f1ec2
commit 4ff9b045fe
10 changed files with 32 additions and 10 deletions

View File

@@ -529,7 +529,7 @@ steps:
commands:
- pip install tensorizer # for tensorizer test
# for basic
- python3 basic/offline_inference/chat.py
- python3 basic/offline_inference/chat.py --attention-backend TRITON_ATTN
- python3 basic/offline_inference/generate.py --model facebook/opt-125m
- python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 basic/offline_inference/classify.py
@@ -2208,7 +2208,7 @@ steps:
commands:
- pip install tensorizer # for tensorizer test
# for basic
- python3 basic/offline_inference/chat.py
- python3 basic/offline_inference/chat.py --attention-backend TRITON_ATTN
- python3 basic/offline_inference/generate.py --model facebook/opt-125m
- python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 basic/offline_inference/classify.py