RYDE-WORK/ktransformers
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/ktransformers.git synced 2026-02-06 22:55:50 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Small fix

Browse Source
This commit is contained in:
chenht2022 2025-02-09 16:25:43 +00:00
parent 6b33f41de4
commit 2d684ee96a
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
doc/en/DeepseekR1_V3_tutorial.md
View File

@ -39,7 +39,8 @@ gpu: 4090D 24G VRAM <br>
| KTrans (8 experts) Prefill token/s | 185.96 | 255.26 | 252.58 | 195.62 | | KTrans (8 experts) Prefill token/s | 185.96 | 255.26 | 252.58 | 195.62 |
| KTrans (6 experts) Prefill token/s | 203.70 | 286.55 | 271.08 | 207.20 | | KTrans (6 experts) Prefill token/s | 203.70 | 286.55 | 271.08 | 207.20 |
**The prefill of KTrans V0.3 is up to <u>x3.45</u> times faster than KTrans V0.2. The decoding speed is the same as KTrans V0.2 (6 experts version) so it is omitted.** **The prefill of KTrans V0.3 is up to <u>x3.45</u> times faster than KTrans V0.2, and is up to <u>x63.53</u> times faster than Llama.**
**The decoding speed is the same as KTrans V0.2 (6 experts version) so it is omitted.**
The main acceleration comes from The main acceleration comes from
- Intel AMX instruction set and our specially designed cache friendly memory layout - Intel AMX instruction set and our specially designed cache friendly memory layout