Skip to content

Commit 1a4da12

Browse files
committed
further shaving int4 layers to improve e2e test time
Summary Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
1 parent 2e2b9b3 commit 1a4da12

File tree

2 files changed

+1
-21
lines changed

2 files changed

+1
-21
lines changed

tests/e2e/vLLM/configs/qwen3_w4a16_grouped_quant.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,4 +6,4 @@ dataset_id: HuggingFaceH4/ultrachat_200k
66
dataset_split: train_sft
77
num_calibration_samples: 20
88

9-
recipe: tests/e2e/vLLM/recipes/WNA16/recipe_w4a16_group_quant_first_20_layers.yaml
9+
recipe: tests/e2e/vLLM/recipes/WNA16/recipe_w4a16_group_quant_first_10_layers.yaml

tests/e2e/vLLM/recipes/WNA16/recipe_w4a16_group_quant_first_20_layers.yaml

Lines changed: 0 additions & 20 deletions
This file was deleted.

0 commit comments

Comments
 (0)