Skip to content
Merged
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
9 changes: 5 additions & 4 deletions fastdeploy/model_executor/layers/quantization/kv_cache.py
Original file line number Diff line number Diff line change
Expand Up @@ -263,10 +263,11 @@ def process_weights_after_loading(self, layer: nn.Layer):
"""
use for loader v1
"""
if layer.cache_k_scale._is_initialized():
layer.cache_k_out_scale.set_value(1 / layer.cache_k_scale)
if layer.cache_v_scale._is_initialized():
layer.cache_v_out_scale.set_value(1 / layer.cache_v_scale)
if "block_wise" not in layer.cache_quant_type_str:
if layer.cache_k_scale._is_initialized():
layer.cache_k_out_scale.set_value(1 / layer.cache_k_scale)
if layer.cache_v_scale._is_initialized():
layer.cache_v_out_scale.set_value(1 / layer.cache_v_scale)

def apply(self, layer):
"""
Expand Down
Loading