mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2025-09-10 06:14:58 +00:00
[ADD] support multi-gpu qlen>1 q5_k
This commit is contained in:
parent
f293803156
commit
f5f79f5c0e
63 changed files with 3271 additions and 1285 deletions
1735
ktransformers/models/modeling_mixtral.py
Normal file
1735
ktransformers/models/modeling_mixtral.py
Normal file
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue