vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 11:49:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
1245 commits 53 branches 29 tags 93 MiB
Commit graph

3 commits

Author SHA1 Message Date
Benjamin F
8484ef8b16
[feat](kt-kernel): adapt MXFP4 MoE backend for DeepSeek-V4-Flash (#1950) 
V4-Flash routed experts ship as native MXFP4 (E2M1 nibble + ue8m0 group
scale). Expose AMXFP4_KGroup_MOE through NativeMoEWrapper, add a loader
that handles V4's `layers.{L}.ffn.experts.{i}.{w1,w3,w2}.{weight,scale}`
naming and converts ue8m0 → bf16 via a lossless bit-cast, register the
model entry, and ship an end-to-end numerical validation script.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-25 18:11:53 +08:00
ErvinXie
9539ab91eb
Cli (#1765) 
* [feat]: add custom option for kt run

* [feat]: depth 3
 2025-12-29 15:18:42 +08:00
ErvinXie
d8046e1bb4
Kt minimax (#1742) 
[feat]: fp8 kernel and kt-cli support
 2025-12-24 15:39:44 +08:00