kvcache-ai/ktransformers
1
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-05-02 04:01:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

[docs]: fix and add MiniMax-M2 tutorial images. (#1752)

Browse Source
This commit is contained in:
Oql
2025-12-25 20:14:35 +08:00
committed by GitHub
parent be668074de
commit 63796374c1
3 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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.