 Xuan-Son Nguyen
|
4d3726278b
model: add llama 4 scaling for mistral-large (deepseek arch) (#17744)
|
1 сар өмнө |
 Herman Semenoff
|
37adc9c6ba
ggml, llama : use defaulted constructors/destructors (#17649)
|
1 сар өмнө |
 Piotr Wilkin (ilintar)
|
746f9ee889
Override SSM_A op for Qwen3 Next to reduce splits (#17587)
|
1 сар өмнө |
 Gilad S.
|
00c361fe53
fix: llama arch implementation (#17665)
|
1 сар өмнө |
|
Xuan-Son Nguyen
|
cd3c118908
model: support Ministral3 (#17644)
|
1 сар өмнө |
|
Piotr Wilkin (ilintar)
|
ff55414c42
model : Qwen3 Next (#16095)
|
1 сар өмнө |
 Georgi Gerganov
|
6783b11fb0
models : fix LFM2 tensors (#17548)
|
1 сар өмнө |
 Aaron Teo
|
877566d512
llama: introduce support for model-embedded sampling parameters (#17120)
|
1 сар өмнө |
 william pan
|
4902eebe33
models : Added support for RND1 Diffusion Language Model (#17433)
|
1 сар өмнө |
 ubergarm
|
23bc779a6e
model : detect GigaChat3-10-A1.8B as deepseek lite (#17420)
|
1 сар өмнө |
 Bartowski
|
e1fcf8b09b
model : add AfmoeForCausalLM support (#16477)
|
2 сар өмнө |
 Sigbjørn Skjæret
|
9008027aa3
hparams : add n_embd_inp() to support extended embed (#16928)
|
2 сар өмнө |
 Li Pengzhan
|
9f052478c2
model : add openPangu-Embedded (#16941)
|
2 сар өмнө |
|
Georgi Gerganov
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
2 сар өмнө |
|
Piotr Wilkin (ilintar)
|
bea04522ff
refactor : llama-model.cpp (#16252)
|
2 сар өмнө |
|
Piotr Wilkin (ilintar)
|
0de0a01576
model : Minimax M2 (#16831)
|
2 сар өмнө |
 Giuseppe Scrivano
|
e58d585604
model : add Granite Hybrid nano types (#16896)
|
2 сар өмнө |
 JJJYmmm
|
d261223d24
model: add support for qwen3vl series (#16780)
|
2 сар өмнө |
 Tianyue-Zhao
|
bacddc049a
model: Add support for CogVLM model (#15002)
|
2 сар өмнө |
|
Georgi Gerganov
|
85a7d8677b
memory : remove KV cache size padding (#16812)
|
2 сар өмнө |
 Johannes Gäßler
|
7a0e900e36
llama: consistent ctx <-> buf order for KV cache (#16746)
|
2 сар өмнө |
|
Johannes Gäßler
|
945501f5ea
llama: fix leaked buffers for mmap + split files (#16765)
|
2 сар өмнө |
|
Sigbjørn Skjæret
|
73a48c9790
convert : enable expert group selection for all models with it (#16691)
|
2 сар өмнө |
|
Sigbjørn Skjæret
|
7cce4f8158
model : set res->t_embd in SmallThinker models (#16782)
|
2 сар өмнө |
 Shunta Saito
|
226f295f4d
model : set res->t_embd in PLaMo2 models (#16766)
|
2 сар өмнө |
 Max Krasnyansky
|
63d2fc46e1
Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)
|
2 сар өмнө |
|
Sigbjørn Skjæret
|
84bf3c6778
model : add BailingMoeV2 support (#16063)
|
2 сар өмнө |
|
Giuseppe Scrivano
|
0398752dd4
model : add Granite Hybrid types (#16635)
|
2 сар өмнө |
|
Johannes Gäßler
|
66b0dbcb2d
llama-model: fix insonsistent ctxs <-> bufs order (#16581)
|
3 сар өмнө |
|
Xuan-Son Nguyen
|
3e3cb19f64
llama-quant: add support for mmproj (#16592)
|
3 сар өмнө |
