huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

add log

Browse Source
This commit is contained in:
OlivierDehaene 2024-01-10 17:17:48 +01:00 committed by Nicolas Patry
parent 8260dc00d8
commit ca20c304b3
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/text_generation_server/models/flash_causal_lm.py
View File

@ -779,6 +779,7 @@ class FlashCausalLM(Model):
if os.getenv("ENABLE_CUDA_GRAPHS", "False") == "True":
try:
logger.info("Experimental support for Cuda Graphs is enabled")
# Warmup cuda graphs for all power of twos until 64
for i in range(6):
self.cuda_graph_warmup(2**i, max_s, max_bt)