huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

adjust the round_up_seq logit to align with prefill warmup phase on HPU

Browse Source 
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
This commit is contained in:
Liu, Kaixuan 2025-05-12 07:21:33 -04:00
parent c94f415af4
commit c264a42aa1
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backends/gaudi/server/text_generation_server/models/causal_lm.py
View File

@ -73,7 +73,7 @@ def torch_compile_for_eager(func):
def round_up_seq(number, k, base): def round_up_seq(number, k, base):
exponent = math.ceil(math.log(number / k, base)) exponent = max(0, math.ceil(math.log(number / k, base)))
return int(k * (base**exponent)) return int(k * (base**exponent))