huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix value

Browse Source
This commit is contained in:
OlivierDehaene 2024-01-10 16:49:00 +01:00 committed by Nicolas Patry
parent 15fdd40587
commit 9904f66966
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
integration-tests/conftest.py
View File

@ -319,7 +319,7 @@ def launcher(event_loop):
env = { env = {
"LOG_LEVEL": "info,text_generation_router=debug", "LOG_LEVEL": "info,text_generation_router=debug",
"ENABLE_CUDA_GRAPHS": "True", "ENABLE_CUDA_GRAPHS": "true",
} }
if not use_flash_attention: if not use_flash_attention:
env["USE_FLASH_ATTENTION"] = "false" env["USE_FLASH_ATTENTION"] = "false"

2
server/text_generation_server/models/flash_causal_lm.py
View File

@ -777,7 +777,7 @@ class FlashCausalLM(Model):
self.device, self.device,
) )
if os.getenv("ENABLE_CUDA_GRAPHS", "False") == "True": if os.getenv("ENABLE_CUDA_GRAPHS", "false") == "true":
try: try:
# Warmup cuda graphs for all power of twos until 64 # Warmup cuda graphs for all power of twos until 64
for i in range(6): for i in range(6):