Çetin
|
b1f48d449e
Add inline tool injection system (Sauron Protocol) with 85+ tools
|
1 maand geleden |
yulo
|
028f93ef98
HIP: RDNA4 tensor core support for MMF (#17077)
|
1 maand geleden |
lhez
|
8e9ddba610
opencl: refine condition for kqv mm (#17392)
|
1 maand geleden |
ubergarm
|
23bc779a6e
model : detect GigaChat3-10-A1.8B as deepseek lite (#17420)
|
1 maand geleden |
Adrien Gallouët
|
28175f857d
cmake : add option to build and link BoringSSL (#17205)
|
1 maand geleden |
Adrien Gallouët
|
9cc4080441
ci : start using OpenSSL (#17235)
|
1 maand geleden |
Jeff Bolz
|
f1ffbba68e
vulkan: disable async for older Intel devices (#17369)
|
1 maand geleden |
Raul Torres
|
2370665e56
CANN: Refactor `evaluate_and_capture_cann_graph` (#17333)
|
1 maand geleden |
nullname
|
21d31e0810
ggml-hexagon: fix swiglu failure at `test-backend-ops` (#17344)
|
1 maand geleden |
Daniel Han
|
dd0f321941
readme : add Unsloth exporting to GGUF in tools (#17411)
|
1 maand geleden |
Xuan-Son Nguyen
|
054a45c3d3
grammar: fix regression caused by #17381 (#17412)
|
1 maand geleden |
Aleksander Grygier
|
4c91f2633f
Improved file naming & structure for UI components (#17405)
|
1 maand geleden |
Piotr Wilkin (ilintar)
|
92c0b387a9
grammar : fix integer overflow (#17381)
|
1 maand geleden |
Georgi Gerganov
|
2286a360ff
sync : ggml
|
1 maand geleden |
YangLe
|
1d321e592b
metal : fix compile on macos 11 (whisper/3533)
|
1 maand geleden |
Georgi Gerganov
|
196f5083ef
common : more accurate sampling timing (#17382)
|
1 maand geleden |
o7si
|
5088b435d4
convert : fix TypeError when loading base model remotely in convert_lora_to_gguf (#17385)
|
1 maand geleden |
Piotr Wilkin (ilintar)
|
845f200b28
ggml : Fix transposed SOLVE_TRI result (#17323)
|
1 maand geleden |
Scott Fudally
|
a7784a8b1d
DGX Spark: UMA support (#17368)
|
1 maand geleden |
Adrien Gallouët
|
79bb743512
ggml : remove useless and error-prone variadic macros (#17399)
|
1 maand geleden |
sudhiarm
|
3ae282a06f
kleidiai: fix zero-size array declaration (#17240)
|
1 maand geleden |
ixgbe
|
5be353ec4a
ggml-cpu:add RISC-V RVV (Zvfh) optimization for FP16 vector scaling (#17314)
|
1 maand geleden |
Giuseppe Scrivano
|
7d77f07325
vulkan: implement ADD1, ARANGE, FILL, SOFTPLUS, STEP, ROUND, CEIL, FLOOR, TRUNC (#17319)
|
1 maand geleden |
Jeff Bolz
|
1fa4551af0
vulkan: support larger argsort (#17313)
|
1 maand geleden |
Jeff Bolz
|
2eba631b81
vulkan: Add copy_transpose shader (#17371)
|
1 maand geleden |
Aleksander Grygier
|
99c53d6558
webui: Add a "Continue" Action for Assistant Message (#16971)
|
1 maand geleden |
Sigbjørn Skjæret
|
07b0e7a5ac
convert : use self.block_count everywhere instead of reading hparams (#17359)
|
1 maand geleden |
Aman Gupta
|
fd7353d5eb
cuda: fix rope fusion for gemma3 (#17378)
|
1 maand geleden |
Piotr Wilkin (ilintar)
|
6fd4f95367
Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition (#17332)
|
1 maand geleden |
Ruben Ortlam
|
980b7cd17e
vulkan: force full subgroups for flash attention to fix intel subgroup crash (#17356)
|
1 maand geleden |