karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 2 Packages Activity

[CI] Fix test_auto_gptq on ROCm CI (#46164)

Browse Source 
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
fxmarty-amd
2026-06-23 16:38:06 -05:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent b28103e1ca
commit 84f13374b3
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/quantization/test_configs.py
+2 -2
View File
@@ -28,7 +28,7 @@ MODEL_ARG_EXPTYPES = [
(
"TheBloke/Llama-2-7B-Chat-GPTQ",
"marlin",
"auto_gptq" if current_platform.is_cuda() else "ERROR",
"auto_gptq" if current_platform.is_cuda_alike() else "ERROR",
),
("TheBloke/Llama-2-7B-Chat-GPTQ", "gptq", "auto_gptq"),
("TheBloke/Llama-2-7B-Chat-GPTQ", "awq", "ERROR"),
@@ -38,7 +38,7 @@ MODEL_ARG_EXPTYPES = [
(
"LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit",
"marlin",
"auto_gptq" if current_platform.is_cuda() else "ERROR",
"auto_gptq" if current_platform.is_cuda_alike() else "ERROR",
),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "gptq", "auto_gptq"),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "awq", "ERROR"),