[ROCm][Quantization][5/N] Refactor quark_moe w8a8-int8 w/ oracle (#46765)
Signed-off-by: amd-sourjya <amd-sourjya@users.noreply.github.com> Co-authored-by: amd-sourjya <amd-sourjya@users.noreply.github.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
co-authored by
amd-sourjya
Cursor
Andreas Karatzas
parent
b5bcb3ce88
commit
1053e248f0
@@ -0,0 +1,5 @@
|
||||
model_name: "amd/Qwen1.5-MoE-A2.7B-Chat-w-int8-a-int8-sym"
|
||||
accuracy_threshold: 0.50
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: "--enforce-eager --max-model-len 4096"
|
||||
@@ -1,6 +1,7 @@
|
||||
Qwen3-0.6B-FP8.yaml
|
||||
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
|
||||
Qwen1.5-MoE-W4A16-CT.yaml
|
||||
Qwen1.5-MoE-A2.7B-Chat-INT8.yaml
|
||||
DeepSeek-V2-Lite-Instruct-FP8.yaml
|
||||
Qwen3-Next-FP8-EP2_MI355.yaml
|
||||
Qwen3-30B-A3B-Thinking-2507-FP8.yaml
|
||||
|
||||
Reference in New Issue
Block a user