Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
# @package _global_

defaults:
- runs/vlm_pruning_base
- _self_

# Bounded all-axis search shared by the maintained 4B lifecycle smoke and
# campaign. Each supported structural axis receives an isolated
# dynamic-versus-physical diagnostic before it can enter MIP selection.
puzzle_dir: ${oc.env:PUZZLETRON_RUN_ROOT,puzzle_runs/qwen3p5_4b_vlm_smoke}
display_name: Qwen3p5 4B VLM all-axis search

model:
automodel_backend: {attn: sdpa}

embedding_pruning:
widths: [2560, 2400]
alignment: 32

pruning:
intermediate_size_list: [8704]
# [query heads, KV groups]: teacher, query-only, KV-only, and joint targets.
attn_heads_list: [[16, 4], [12, 4], [8, 2], [6, 2]]
attention_scored_axes: [kv_groups, q_heads_per_group]
gdn_scored_axes:
- gdn_key_groups
- gdn_value_heads_per_group
- gdn_key_head_dim
- gdn_value_head_dim

sort:
deferred_axes: []

width_sanity:
hidden_width_diagnostic: true
axes:
- hidden_width
- kv_groups
- q_heads_per_group
- ffn_intermediate
- gdn_key_groups
- gdn_value_heads_per_group
- gdn_key_head_dim
- gdn_value_head_dim
one_case_per_axis: true
target_count_per_axis: 1
layer_count: 1
eval_samples: 2
target_values:
hidden_width: 2400
kv_groups: 2
q_heads_per_group: 3
ffn_intermediate: 8704
gdn_key_groups: 14
gdn_value_heads_per_group: 1
gdn_key_head_dim: 112
gdn_value_head_dim: 112

depth_importance:
enabled: true
max_removals: 1
max_subblocks_to_remove: 1
eval_samples: 2

search_space:
axes:
hidden_width: {enabled: true, teacher_value: 2560, values: [2400]}
kv_groups: {enabled: true, teacher_value: 4, values: [2]}
q_heads_per_group: {enabled: true, teacher_value: 4, values: [3]}
ffn_intermediate: {enabled: true, teacher_value: 9216, values: [8704]}
gdn_key_groups: {enabled: true, teacher_value: 16, values: [14]}
gdn_value_heads_per_group: {enabled: true, teacher_value: 2, values: [1]}
gdn_key_head_dim: {enabled: true, teacher_value: 128, values: [112]}
gdn_value_head_dim: {enabled: true, teacher_value: 128, values: [112]}

mip:
depth_scenario_count: 2
runs:
params-80:
search_space: &all_axis_search
depth: [0, 1]
embedding: [2560, 2400]
axes_default: all
axes: {ffn.intermediate_size: all}
solver: &all_axis_solver
backend: auto
num_solutions: 1
min_hamming_distance: 1
max_seconds_per_solution: 30
homogeneous: &no_homogeneous {enabled: false}
memory-85:
search_space: *all_axis_search
solver: *all_axis_solver
homogeneous: *no_homogeneous
Loading
Loading