llama.cpp
Optimization: Qwen3 next autoregressive pass
#17996
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
6
Changes
View On
GitHub
Commits
It's Qwen3 Next, the lean mean token generation machine!
pwilkin
committed
9 days ago
Apply patches from thread
pwilkin
committed
9 days ago
Remove recurrent version, only keep chunked and autoregressive
pwilkin
committed
9 days ago
Remove unnecessary conts and asserts
pwilkin
committed
9 days ago
Remove more extra conts and asserts
pwilkin
committed
9 days ago
Cleanup masking
pwilkin
committed
8 days ago
Loading