llama.cpp
model: MTP support for Qwen3-Next
#25589
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
9
Changes
View On
GitHub
model: MTP support for Qwen3-Next
#25589
yomaytk
merged 9 commits into
ggml-org:master
from
yomaytk:qwen3next-mtp
yomaytk
requested a review
from
CISC
31 days ago
github-actions
added
model
github-actions
added
conversion
yomaytk
commented on 2026-07-12
yomaytk
requested a review
from
am17an
31 days ago
am17an
approved these changes on 2026-07-13
yomaytk
commented on 2026-07-14
yomaytk
force pushed
from
dd723c9a
to
2e265efe
30 days ago
yomaytk
commented on 2026-07-14
CISC
commented on 2026-08-02
mtp for qwen3nex
4a0458ad
fix for python type-check
fa3ab90c
Fix to compute num_mtp from directly mtp layer
d80b0bdb
define opt_num_mtp_layers in _QwenMtpMixin and fix some comments
590dda5e
Fix for python type check
3c663971
Update gguf-py/gguf/constants.py
2e0e9e2b
rebase and add load_mtp flags
f3e02e77
yomaytk
force pushed
from
efc60fe9
to
f3e02e77
10 days ago
CISC
approved these changes on 2026-08-03
Update src/models/qwen3next.cpp
d584479b
Update src/models/qwen3next.cpp
e481b2a3
yomaytk
added
merge ready
CISC
approved these changes on 2026-08-03
yomaytk
merged
4ed2b13f
into master
10 days ago
yomaytk
deleted the qwen3next-mtp branch
10 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
CISC
am17an
Assignees
No one assigned
Labels
model
merge ready
conversion
Milestone
No milestone
Login to write a write a comment.
Login via GitHub