llama.cpp
Optimization: Qwen3 next autoregressive pass
#17996
Merged
Overview
Commits
6
Changes
View On GitHub

Optimization: Qwen3 next autoregressive pass #17996

pwilkin merged 6 commits into ggml-org:master from pwilkin:lean_mean_token_machine
pwilkin
pwilkin pwilkin requested a review from CISC CISC 6 days ago
jeffbolznv
jacekpoplawski
IIIIIllllIIIIIlllll
pwilkin
othermod
IIIIIllllIIIIIlllll
CISC
CISC approved these changes on 2025-12-13
pwilkin
CISC
IIIIIllllIIIIIlllll
mpapili
github-actions github-actions added model
heislera763
heislera763
CISC
Som-anon
jeffbolznv
fuutott
IIIIIllllIIIIIlllll
ggerganov
ggerganov commented on 2025-12-13
Som-anon
kiuckhuang
pwilkin It's Qwen3 Next, the lean mean token generation machine!
b739b11d
pwilkin pwilkin force pushed from 4a494ab7 to b739b11d 4 days ago
pwilkin Apply patches from thread
bd7b7105
pwilkin Remove recurrent version, only keep chunked and autoregressive
9357f6df
pwilkin Remove unnecessary conts and asserts
a58f2aca
pwilkin Remove more extra conts and asserts
2c44d215
pwilkin
ggerganov
ggerganov commented on 2025-12-15
lovedheart
pwilkin Cleanup masking
b1477de0
pwilkin
ggerganov
ggerganov approved these changes on 2025-12-16
pwilkin pwilkin merged a5251ca1 into master 3 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
model
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum