vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-26 10:50:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

[docs]: fix and add MiniMax-M2 tutorial images. (#1752)
Some checks failed
Book-CI / test (push) Has been cancelled
Details
Book-CI / test-1 (push) Has been cancelled
Details
Book-CI / test-2 (push) Has been cancelled
Details
Deploy / deploy (macos-latest) (push) Has been cancelled
Details
Deploy / deploy (ubuntu-latest) (push) Has been cancelled
Details
Deploy / deploy (windows-latest) (push) Has been cancelled
Details

Browse source
This commit is contained in:
Oql 2025-12-25 20:14:35 +08:00 • committed by GitHub
parent be668074de
commit 63796374c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

BIN
doc/assets/MiniMax-M2_comparison.png
View file

Binary file not shown.
Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 73 KiB

After

Width:  |  Height:  |  Size: 75 KiB

Before After
Before After

BIN
doc/assets/MiniMax-M2_speed.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 146 KiB

2
doc/en/kt-kernel/MiniMax-M2.1-Tutorial.md
View file

@ -168,6 +168,8 @@ The following benchmarks were measured with single concurrency (Prefill tps / De
| 1 x RTX 5090 (32 GB) | 2 x AMD EPYC 9355 | PCIe 5.0 | 408 / 32.1 | 1196 / 31.4 | 2540 / 27.6 |
| 2 x RTX 5090 (32 GB) | 2 x AMD EPYC 9355 | PCIe 5.0 | 414 / 35.9 | 1847 / 35.5 | 4007 / 33.1 |
![Throughput in 2 x RTX 5090](../../assets/MiniMax-M2_speed.png)
### Comparison with llama.cpp
We benchmarked KT-Kernel + Sglang against llama.cpp to demonstrate the performance advantages of our CPU-GPU heterogeneous inference approach.