Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 10:47:38 +02:00
Code Issues Packages Projects Releases Wiki Activity
8,634 Commits 759 Branches 7,325 Tags
b8634
Commit Graph
3 Commits
Author SHA1 Message Date
Xuan-Son Nguyen 59db9a357d llama: dynamic head_dim and n_rot for SWA (#20301) 
* llama: dynamic head_dim and n_rot for SWA

* also add gguf_writer wrappers

* fix build

* build_rope_shift arg reorder
 2026-03-09 22:22:39 +01:00
Sigbjørn Skjæret 35bee031e1 graph : remove redundant scale_w parameter (#20235) 2026-03-08 18:58:28 +01:00
Xuan-Son NguyenSigbjørn SkjæretJulien Denize
 		cd3c118908 model: support Ministral3 (#17644) 
* conversion script

* support ministral 3

* maybe this is better?

* add TODO for rope_yarn_log_mul

* better ppl (tested on 14B-Instruct)

* Add Ministral3 support to Mistral format

* improve arch handling

* add sizes

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* nits

---------

Co-authored-by: Julien Denize <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
 2025-12-01 12:26:52 +01:00