RYDE-WORK/ktransformers
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/ktransformers.git synced 2026-02-06 06:23:15 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

⚡ fix typo

Browse Source
This commit is contained in:
liam 2025-02-10 09:52:48 +08:00
parent fd481af193
commit cff68532ce
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
doc/en/DeepseekR1_V3_tutorial.md
View File

@ -1,6 +1,6 @@
# Report # Report
## Prerequisites ## Prerequisites
We run our best performance tests on <br> We run our best performance tests(V0.2) on <br>
cpu: Intel(R) Xeon(R) Gold 6454S 1T DRAM(2 NUMA nodes)<br> cpu: Intel(R) Xeon(R) Gold 6454S 1T DRAM(2 NUMA nodes)<br>
gpu: 4090D 24G VRAM <br> gpu: 4090D 24G VRAM <br>
## Bench result ## Bench result
@ -50,7 +50,7 @@ The main acceleration comes from
*From our research on DeepSeekV2, DeepSeekV3 and DeepSeekR1, *From our research on DeepSeekV2, DeepSeekV3 and DeepSeekR1,
when we slightly decrease the activation experts num in inference, when we slightly decrease the activation experts num in inference,
the output quality doesn't change,But the speed of decoding and prefill the output quality doesn't change. But the speed of decoding and prefill
is speed up which is inspiring. So our showcase makes use of this finding* is speed up which is inspiring. So our showcase makes use of this finding*
## how to run ## how to run