kvcache-ai/ktransformers
1
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-27 17:51:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Kimi-K2.md

Browse Source
This commit is contained in:
Atream
2025-07-12 12:44:41 +08:00
committed by GitHub
parent df19681ec4
commit 34d2829f24
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
doc/en/Kimi-K2.md
View File

@@ -5,7 +5,7 @@
### Overview
We are very pleased to announce that Ktransformers now supports Kimi-K2.
On a single-socket CPU with one consumer-grade GPU, running the Q4_K_M model yields roughly 10 TPS and requires about 600 GB of VRAM.
On a single-socket CPU with one consumer-grade GPU, running the Q4_K_M model yields roughly 10 TPS and requires about 600 GB of DRAM.
With a dual-socket CPU and sufficient system memory, enabling NUMA optimizations increases performance to about 14 TPS.
### Model & Resource Links