Skip to content

[WIP][Testing] Add VL e2e tests #1400

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

[WIP][Testing] Add VL e2e tests #1400

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0a068d2
add qwen vl test
kylesayrs Apr 29, 2025
c11d0d2
add multimodal ignores to all recipes
kylesayrs Apr 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions tests/e2e/vLLM/configs/vl_w4a16_actorder_group_qwen_vl.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
cadence: "weekly"
test_type: "regression"
model: Qwen/Qwen2.5-VL-7B-Instruct
model_class: Qwen2_5_VLForConditionalGeneration
recipe: tests/e2e/vLLM/recipes/actorder/recipe_w4a16_actorder_group.yaml
dataset_id: lmms-lab/flickr30k
dataset_config: default
dataset_split: test
scheme: W4A16_actorder_group
save_dir: Qwen2.5-VL-7B-Instruct-v1.0-actorder-group
2 changes: 1 addition & 1 deletion tests/e2e/vLLM/recipes/WNA16/recipe_w4a16_channel_quant.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
quant_stage:
quant_modifiers:
GPTQModifier:
ignore: [lm_head]
ignore: ["lm_head", "re:vision_tower.*", "re:multi_modal_projector.*", "re:visual.*", "re:vision_model.*"]
config_groups:
group_0:
weights: {num_bits: 4, type: int, symmetric: true, strategy: channel, dynamic: false}
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/vLLM/recipes/WNA16/recipe_w8a16_channel_quant.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
quant_stage:
quant_modifiers:
GPTQModifier:
ignore: [lm_head]
ignore: ["lm_head", "re:vision_tower.*", "re:multi_modal_projector.*", "re:visual.*", "re:vision_model.*"]
config_groups:
group_0:
weights: {num_bits: 8, type: int, symmetric: true, strategy: channel, dynamic: false}
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/vLLM/recipes/WNA16_2of4/2of4_w4a16_group-128_recipe.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ quantization_stage:
run_type: oneshot
quantization_modifiers:
GPTQModifier:
ignore: ["lm_head"]
ignore: ["lm_head", "re:vision_tower.*", "re:multi_modal_projector.*", "re:visual.*", "re:vision_model.*"]
config_groups:
group_0:
weights:
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/vLLM/recipes/WNA16_2of4/2of4_w4a16_recipe.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ quantization_stage:
run_type: oneshot
quantization_modifiers:
GPTQModifier:
ignore: ["lm_head"]
ignore: ["lm_head", "re:vision_tower.*", "re:multi_modal_projector.*", "re:visual.*", "re:vision_model.*"]
config_groups:
group_0:
weights:
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/vLLM/recipes/actorder/recipe_w4a16_actorder_group.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
quant_stage:
quant_modifiers:
GPTQModifier:
ignore: ["lm_head"]
ignore: ["lm_head", "re:vision_tower.*", "re:multi_modal_projector.*", "re:visual.*", "re:vision_model.*"]
config_groups:
group_0:
weights:
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/vLLM/recipes/kv_cache/gptq.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ quant_stage:
{num_bits: 8, type: float, symmetric: true, strategy: tensor}
GPTQModifier:
sequential_update: false
ignore: ["lm_head"]
ignore: ["lm_head", "re:vision_tower.*", "re:multi_modal_projector.*", "re:visual.*", "re:vision_model.*"]
config_groups:
group_0:
weights:
Expand Down