 Sigbjørn Skjæret
|
169ee68ffb
model : remove modern-bert iswa template (#18529)
|
4 weeks ago |
 tt
|
ced765be44
model: support youtu-vl model (#18479)
|
4 weeks ago |
 o7si
|
d0a6a31470
model : add support for JinaBertModel with non-gated ffn (#18475)
|
4 weeks ago |
 HelloKS
|
f4f5019254
model: add Solar Open model (#18511)
|
4 weeks ago |
 momonga
|
9c675c7140
model : Plamo3 support (#17304)
|
1 month ago |
 Johannes Gäßler
|
026d2ad472
llama: fix magic number of 999 for GPU layers (#18266)
|
1 month ago |
 Xuan-Son Nguyen
|
4cbafad4f0
model: support MiMo-V2-Flash (#18328)
|
1 month ago |
 Saba Fallah
|
54132f1b1f
model : support for LlamaBidirectionalModel architecture (#18220)
|
1 month ago |
 Alessandro98-git
|
96e33a814e
model : fix div-by-zero for Nemotron V2 (#18309)
|
1 month ago |
 Ryan Mangeno
|
dfc959b886
model : Granite Embedding support (#15641)
|
1 month ago |
|
Johannes Gäßler
|
57c1e05643
llama: offload output layer to GPU first (#18148)
|
1 month ago |
|
Xuan-Son Nguyen
|
ef83fb8601
model: fix LFM2 missing tensors (#18105)
|
1 month ago |
|
Xuan-Son Nguyen
|
3d86c6c2b5
model: support GLM4V vision encoder (#18042)
|
1 month ago |
 Daniel Bevenius
|
2995341730
llama : add support for NVIDIA Nemotron 3 Nano (#18058)
|
1 month ago |
|
HelloKS
|
9d52f17ae3
model : add KORMo model (#18032)
|
1 month ago |
|
Johannes Gäßler
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
1 month ago |
|
Xuan-Son Nguyen
|
0759b09c90
graph: add f_attn_temp_offset (#18025)
|
1 month ago |
 Georgi Gerganov
|
609a2d0268
models : fix YaRN regression + consolidate logic (#18006)
|
1 month ago |
|
Georgi Gerganov
|
7bed317f53
models : fix the attn_factor for mistral3 graphs + improve consistency (#17945)
|
1 month ago |
 Eric Zhang
|
b677721819
model : Qwen3-Next-80B-A3B has 48 layers (#17898)
|
1 month ago |
|
Sigbjørn Skjæret
|
42b12b5608
model : nit, DeepSeek V1 MoE is 16B and GigaChat is 20B (#12652)
|
1 month ago |
 philip-essential
|
1d2a1ab73d
model : support Rnj-1 (#17811)
|
1 month ago |
|
Xuan-Son Nguyen
|
4d3726278b
model: add llama 4 scaling for mistral-large (deepseek arch) (#17744)
|
1 month ago |
 Herman Semenoff
|
37adc9c6ba
ggml, llama : use defaulted constructors/destructors (#17649)
|
1 month ago |
 Piotr Wilkin (ilintar)
|
746f9ee889
Override SSM_A op for Qwen3 Next to reduce splits (#17587)
|
1 month ago |
 Gilad S.
|
00c361fe53
fix: llama arch implementation (#17665)
|
1 month ago |
|
Xuan-Son Nguyen
|
cd3c118908
model: support Ministral3 (#17644)
|
1 month ago |
|
Piotr Wilkin (ilintar)
|
ff55414c42
model : Qwen3 Next (#16095)
|
2 months ago |
|
Georgi Gerganov
|
6783b11fb0
models : fix LFM2 tensors (#17548)
|
2 months ago |
 Aaron Teo
|
877566d512
llama: introduce support for model-embedded sampling parameters (#17120)
|
2 months ago |
