Skip to content

[BugFix] GPT inference error when pipeline_para_size > 1 and int8_mode != 0 #750

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[BugFix] GPT inference error when pipeline_para_size > 1 and int8_mode != 0 #750

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
63 changes: 32 additions & 31 deletions examples/pytorch/gpt/utils/gpt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -403,38 +403,39 @@ def load_to_torch(file_path: str, is_load: bool):
layer_num = self.layer_num
if self.int8_mode != 0:
for i in range(layer_num):
self.int8_w[i + 0 * layer_num], self.scale[i + 0 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[2 * layer_num + i])
self.int8_w[i + 1 * layer_num], self.scale[i + 1 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[4 * layer_num + i])
self.int8_w[i + 2 * layer_num], self.scale[i + 2 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[8 * layer_num + i])
self.int8_w[i + 3 * layer_num], self.scale[i + 3 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[10 * layer_num + i])

# We clear the original weights since they are no longer needed
if self.int8_mode == 1:
self.w[2 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[4 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[8 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[10 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])

if self.has_adapters:
self.int8_w[i + 4 * layer_num], self.scale[i + 4 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[12 * layer_num + i + self.adapter_offset])
self.int8_w[i + 5 * layer_num], self.scale[i + 5 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[14 * layer_num + i + self.adapter_offset])
self.int8_w[i + 6 * layer_num], self.scale[i + 6 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[16 * layer_num + i + self.adapter_offset])
self.int8_w[i + 7 * layer_num], self.scale[i + 7 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[18 * layer_num + i + self.adapter_offset])

# Similar to above:
if is_load(i):
self.int8_w[i + 0 * layer_num], self.scale[i + 0 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[2 * layer_num + i])
self.int8_w[i + 1 * layer_num], self.scale[i + 1 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[4 * layer_num + i])
self.int8_w[i + 2 * layer_num], self.scale[i + 2 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[8 * layer_num + i])
self.int8_w[i + 3 * layer_num], self.scale[i + 3 *
layer_num] = self.weight_transpose_calibrate_quantize(self.w[10 * layer_num + i])

# We clear the original weights since they are no longer needed
if self.int8_mode == 1:
self.w[12 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[14 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[16 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[18 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[2 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[4 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[8 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[10 * layer_num + i] = torch.empty(0).to(str_type_map[self.inference_data_type])

if self.has_adapters:
self.int8_w[i + 4 * layer_num], self.scale[i + 4 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[12 * layer_num + i + self.adapter_offset])
self.int8_w[i + 5 * layer_num], self.scale[i + 5 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[14 * layer_num + i + self.adapter_offset])
self.int8_w[i + 6 * layer_num], self.scale[i + 6 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[16 * layer_num + i + self.adapter_offset])
self.int8_w[i + 7 * layer_num], self.scale[i + 7 * layer_num] = self.weight_transpose_calibrate_quantize(
self.w[18 * layer_num + i + self.adapter_offset])

# Similar to above:
if self.int8_mode == 1:
self.w[12 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[14 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[16 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
self.w[18 * layer_num + i + self.adapter_offset] = torch.empty(0).to(str_type_map[self.inference_data_type])
return True


Expand Down