huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update mistral past.

Browse Source
This commit is contained in:
Nicolas Patry 2024-07-01 13:19:26 +00:00
parent 8fa8cda660
commit 1bd52157d8
2 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py
View File

@ -512,7 +512,9 @@ class FlashMistralForCausalLM(torch.nn.Module):
elif self.max_past is not None:
# Clamp in decode mode as paged attention requires clamped values whereas the flash attention
# kernel requires the true values
input_lengths = torch.clamp(input_lengths, max=self.max_past_tensor)
input_lengths.input_lengths = torch.clamp(
input_lengths.input_lengths, max=self.max_past_tensor
)
inputs_embeds = self.embed_tokens(input_ids)
hidden_states = self.model(

4
server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py
View File

@ -647,7 +647,9 @@ class FlashMixtralForCausalLM(torch.nn.Module):
elif self.max_past is not None:
# Clamp in decode mode as paged attention requires clamped values whereas the flash attention
# kernel requires the true values
input_lengths = torch.clamp(input_lengths, max=self.max_past_tensor)
input_lengths.input_lengths = torch.clamp(
input_lengths.input_lengths, max=self.max_past_tensor
)
hidden_states = self.model(
input_ids,