From 02b0eaaba09e26e9e57c4bf49d4b5672a950bb8c Mon Sep 17 00:00:00 2001 From: root Date: Wed, 24 Jul 2024 03:35:53 +0000 Subject: [PATCH] MODEL_ID propagation fix --- server/text_generation_server/models/flash_causal_lm.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py index 5db62431..1701288e 100644 --- a/server/text_generation_server/models/flash_causal_lm.py +++ b/server/text_generation_server/models/flash_causal_lm.py @@ -46,6 +46,7 @@ from text_generation_server.models.globals import ( get_adapter_to_index, MODEL_ID, ) +import text_generation_server.models.globals as globals_vars from text_generation_server.layers.attention import Seqlen from text_generation_server.utils import StoppingCriteria, HeterogeneousNextTokenChooser from text_generation_server.utils.dist import MEMORY_FRACTION @@ -1157,7 +1158,7 @@ class FlashCausalLM(Model): tunableop_filepath = os.path.join( 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(