vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-29 12:19:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Kt minimax (#1742)

Browse source 
[feat]: fp8 kernel and kt-cli support
This commit is contained in:
ErvinXie 2025-12-24 15:39:44 +08:00 • committed by GitHub
parent e7d277d163
commit d8046e1bb4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
65 changed files with 12111 additions and 2502 deletions
Download patch file Download diff file Expand all files Collapse all files

2
kt-kernel/python/utils/llamafile.py
View file

@ -219,4 +219,4 @@ class LlamafileMoEWrapper(BaseMoEWrapper):
self.cpu_infer.sync()
# Drop original weights after loading
self.weights_to_keep = None
self.weights_to_keep = None