From a7cf5e856729376631ddd713bb1cc2aab546ba32 Mon Sep 17 00:00:00 2001 From: Mohit Sharma Date: Tue, 7 Jan 2025 07:19:31 +0000 Subject: [PATCH] update log statement --- server/text_generation_server/layers/attention/kv_cache.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/layers/attention/kv_cache.py b/server/text_generation_server/layers/attention/kv_cache.py index a0823c8d..b02b46c9 100644 --- a/server/text_generation_server/layers/attention/kv_cache.py +++ b/server/text_generation_server/layers/attention/kv_cache.py @@ -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