biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Super tiny little typo fix (#10633)

Browse Source
This commit is contained in:
fzyzcjy
2024-11-25 21:08:30 +08:00
committed by GitHub
parent ed46f14321
commit 2b0879bfc2
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/quantization/fp8_e5m2_kvcache.rst
View File

@@ -4,7 +4,7 @@ FP8 E5M2 KV Cache
================== ==================
The int8/int4 quantization scheme requires additional scale GPU memory storage, which reduces the expected GPU memory benefits. The int8/int4 quantization scheme requires additional scale GPU memory storage, which reduces the expected GPU memory benefits.
The FP8 data format retains 2~3 mantissa bits and can convert float/fp16/bflaot16 and fp8 to each other. The FP8 data format retains 2~3 mantissa bits and can convert float/fp16/bfloat16 and fp8 to each other.
Here is an example of how to enable this feature: Here is an example of how to enable this feature: