 Georgi Gerganov
|
f28bc4c286
llama : make loras compatible with repacking (#12593)
|
9 月之前 |
 Akarshan Biswas
|
f17a3bb4e8
SYCL: implement memset ggml backend buffer interface (#12580)
|
9 月之前 |
 Slobodan Josic
|
bd40678df7
HIP: Add support for RDNA4 targets (#12372)
|
9 月之前 |
|
Georgi Gerganov
|
b3298fa47a
metal : refactor mat-vec code (#12569)
|
9 月之前 |
 Michał Moskal
|
2447ad8a98
upgrade to llguidance 0.7.10 (#12576)
|
9 月之前 |
 Ivy233
|
02082f1519
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA backend (#12566)
|
9 月之前 |
|
Georgi Gerganov
|
df4d20cd53
convert : fix squeeze for ssm_conv tensors (#12573)
|
9 月之前 |
|
Georgi Gerganov
|
5ed38b6852
ggml : fix MUL_MAT_ID repack with Q8_K (#12544)
|
9 月之前 |
 R0CKSTAR
|
fd7855f8f5
doc: [MUSA] minor changes (#12583)
|
9 月之前 |
 Sigbjørn Skjæret
|
53af4dba42
convert: fix Mistral3/Gemma3 model hparams init (#12571)
|
10 月之前 |
 Eric Curtin
|
ef19c71769
run: de-duplicate fmt and format functions and optimize (#11596)
|
10 月之前 |
 Dan Johansson
|
053b3f9aae
ggml-cpu : update KleidiAI to v1.5.0 (#12568)
|
10 月之前 |
|
Akarshan Biswas
|
e2f560175a
SYCL: disable Q4_0 reorder optimization (#12560)
|
10 月之前 |
|
Dan Johansson
|
36ee06dd2d
docs : add build instructions for KleidiAI (#12563)
|
10 月之前 |
|
R0CKSTAR
|
3cd3a39532
ci: [MUSA] add CI and update doc (#12562)
|
10 月之前 |
|
Georgi Gerganov
|
2d77d88e70
context : fix worst-case reserve outputs (#12545)
|
10 月之前 |
|
Akarshan Biswas
|
c95fa362b3
ci: [SYCL] ggml-ci Use main GPU and enable sysman (#12547)
|
10 月之前 |
 lhez
|
2b65ae3029
opencl: simplify kernel embedding logic in cmakefile (#12503)
|
10 月之前 |
|
Akarshan Biswas
|
48d7021c61
CI: fix SYCL build (#12546)
|
10 月之前 |
 Tei Home
|
3361e2deba
docs: update: improve the Fedoa CUDA guide (#12536)
|
10 月之前 |
 compilade
|
00d53800e0
llama-vocab : add SuperBPE pre-tokenizer (#12532)
|
10 月之前 |
|
R0CKSTAR
|
7ea75035b6
CUDA: Fix clang warnings (#12540)
|
10 月之前 |
 Prajwal B Mehendarkar
|
c54f6b7988
mmap : skip resource limit checks on AIX (#12541)
|
10 月之前 |
 Jeff Bolz
|
9b169a4d4e
vulkan: fix mul_mat_vec failure in backend tests (#12529)
|
10 月之前 |
 Marius Gerdes
|
77f9c6bbe5
server : Add verbose output to OAI compatible chat endpoint. (#12246)
|
10 月之前 |
 Lars Sonchocky-Helldorf
|
18b663d8e4
install : add macports (#12518)
|
10 月之前 |
 Xuan-Son Nguyen
|
fbdfefe74e
llama : gemma3 : use output tensor if it exists in model weight (#12506)
|
10 月之前 |
|
Georgi Gerganov
|
ba932dfb50
ggml : fix quantized cpy op (#12310)
|
10 月之前 |
|
R0CKSTAR
|
fac63a3d78
musa: refine compute capability (#12493)
|
10 月之前 |
|
Jeff Bolz
|
eddfb43850
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505)
|
10 月之前 |
