Skip to content

GitLab

Commit 5d35160b authored by zhuwenwen's avatar zhuwenwen
Browse files

update blockwise_int8.py

parent e34d3444
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/quantization/blockwise_int8.py
View file @ 5d35160b
...@@ -139,7 +139,6 @@ class BlockInt8LinearMethod(LinearMethodBase): ...@@ -139,7 +139,6 @@ class BlockInt8LinearMethod(LinearMethodBase):
assert self.quant_config.weight_block_size is not None assert self.quant_config.weight_block_size is not None
assert self.quant_config.is_checkpoint_int8_serialized assert self.quant_config.is_checkpoint_int8_serialized
self.tritonsingleton= W8a8GetCacheJSON()
def create_weights( def create_weights(
self, self,
...@@ -337,6 +336,7 @@ class BlockInt8MoEMethod: ...@@ -337,6 +336,7 @@ class BlockInt8MoEMethod:
self.quant_config = quant_config self.quant_config = quant_config
assert self.quant_config.weight_block_size is not None assert self.quant_config.weight_block_size is not None
assert self.quant_config.is_checkpoint_int8_serialized assert self.quant_config.is_checkpoint_int8_serialized
self.tritonsingleton= W8a8GetCacheJSON()
def create_weights( def create_weights(
self, self,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment