huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

MODEL_ID propagation fix

Browse Source
This commit is contained in:
root 2024-07-24 03:35:53 +00:00
parent a895029424
commit 02b0eaaba0
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
server/text_generation_server/models/flash_causal_lm.py
View File

@ -46,6 +46,7 @@ from text_generation_server.models.globals import (
get_adapter_to_index, get_adapter_to_index,
MODEL_ID, MODEL_ID,
) )
import text_generation_server.models.globals as globals_vars
from text_generation_server.layers.attention import Seqlen from text_generation_server.layers.attention import Seqlen
from text_generation_server.utils import StoppingCriteria, HeterogeneousNextTokenChooser from text_generation_server.utils import StoppingCriteria, HeterogeneousNextTokenChooser
from text_generation_server.utils.dist import MEMORY_FRACTION from text_generation_server.utils.dist import MEMORY_FRACTION
@ -1157,7 +1158,7 @@ class FlashCausalLM(Model):
tunableop_filepath = os.path.join( tunableop_filepath = os.path.join(
HUGGINGFACE_HUB_CACHE, HUGGINGFACE_HUB_CACHE,
f"tunableop_{MODEL_ID.replace('/', '-')}_tp{self.world_size}_rank{self.rank}.csv", f"tunableop_{globals_vars.MODEL_ID.replace('/', '-')}_tp{self.world_size}_rank{self.rank}.csv",
) )
log_master( log_master(