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

add prepare_for_prefill

Browse Source
This commit is contained in:
OlivierDehaene 2024-09-30 17:58:14 +02:00
parent 0e31619893
commit 173bc99ab3
No known key found for this signature in database
GPG Key ID: BB104D67809DA93C
2 changed files with 381 additions and 494 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

874
server/text_generation_server/models/flash_causal_lm.py
View File

File diff suppressed because it is too large Load Diff

1
server/text_generation_server/utils/segments.py
View File

@ -7,6 +7,7 @@ from typing import List, Tuple, Union
import torch
# FIXME: this should be optimized
def find_segments(
adapter_indices: Union[torch.Tensor, List[int]]
) -> Tuple[List[int], List[int]]: