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

update log statement

Browse Source
This commit is contained in:
Mohit Sharma 2025-01-07 07:19:31 +00:00
parent 43370a1f82
commit a7cf5e8567
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/layers/attention/kv_cache.py
View File

@ -133,7 +133,7 @@ class KVCache:
# We have scales, but not the correct FP8 cache type, so warn once.
log_once(
logger.info,
"Ignoring FP8 KV cache scales, supported only for flashinfer on CUDA and paged attention on ROCm",
"Ignoring FP8 KV cache scales, supported only for float8_e4m3fn KV cache with flashinfer on CUDA and paged attention on ROCm",
)
return False