 rmatif
|
6bdda13981
opencl: add tiled mul_mat_f16_f32 (#14535)
|
6 ay önce |
 lhez
|
0b8855775c
opencl: add `set_rows` for `f16` and `f32` (#14547)
|
6 ay önce |
 Ryan Mangeno
|
4bb625b713
Smoldocling support (#14597)
|
6 ay önce |
 Aman Gupta
|
11ee0fea2a
Docs: script to auto-generate ggml operations docs (#14598)
|
6 ay önce |
 Eric Zhang
|
a457551332
cmake : do not search for curl libraries by ourselves (#14613)
|
6 ay önce |
 Akarshan Biswas
|
704bb7a71c
SYCL: Initial set_rows kernel implementation (#14562)
|
6 ay önce |
 Xuan-Son Nguyen
|
435a6d10d6
llama : minor coding style fix for smollm3 (#14605)
|
6 ay önce |
|
Eric Zhang
|
f9a867f592
cmake : bump llguidance version to v1.0.1 (#14609)
|
6 ay önce |
|
Eric Zhang
|
ac44eb6c80
cmake : llguidance build parser library only (#14608)
|
6 ay önce |
 compilade
|
a57d1bcb3c
cuda : support Falcon-H1 state size for SSM_SCAN (#14602)
|
6 ay önce |
|
Xuan-Son Nguyen
|
cb9178f885
llama : remove llm_graph_input_one (#14603)
|
6 ay önce |
|
compilade
|
4a5686da22
llama : support Jamba hybrid Transformer-Mamba models (#7531)
|
6 ay önce |
|
Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
6 ay önce |
 Miaoqian Lin
|
26a48ad699
ggml : prevent integer overflow in gguf tensor size calculation (#14595)
|
6 ay önce |
 Dowon
|
ffd59e7d18
model : add skt/A.X-4.0 model vocabulary (#14589)
|
6 ay önce |
 Sigbjørn Skjæret
|
105554595f
llama : remove unintended whitespace (#14592)
|
6 ay önce |
 ibrahim khadraoui
|
04655063c4
model : add support for Falcon-H1 family (#14534)
|
6 ay önce |
|
Xuan-Son Nguyen
|
20b7bf8a32
convert : fix smollm3 jinja template (#14586)
|
6 ay önce |
 Jeff Bolz
|
6efcd65945
vulkan: optimize flash attention split_k_reduce (#14554)
|
6 ay önce |
 stevenkuang
|
699f4392a3
model : fix hunyuan moe chat template (#14584)
|
6 ay önce |
|
Xuan-Son Nguyen
|
08382869a2
model : add SmolLM3 (#14581)
|
6 ay önce |
|
compilade
|
bb4f7a9e4e
memory : fix broken batch splits for recurrent cache (#14575)
|
6 ay önce |
|
Jeff Bolz
|
b8eeb8741d
vulkan : fix rope with partial rotation and non-cont src (#14582)
|
6 ay önce |
 Alawode Oluwandabira
|
17a1f0d2d4
server: Add ability to mount server at prefix (#14544)
|
6 ay önce |
|
Xuan-Son Nguyen
|
8f22dc0a53
model : add hunyuan moe (#14425)
|
6 ay önce |
|
Jeff Bolz
|
53903ae6fa
vulkan: increase timeout for CI (#14574)
|
6 ay önce |
 Georgi Gerganov
|
4d0dcd4a06
cuda : fix rope with partial rotation and non-cont src (#14580)
|
6 ay önce |
|
Aman Gupta
|
75c91de6e9
CUDA: add bilinear interpolation for upscale (#14563)
|
6 ay önce |
 R0CKSTAR
|
68155c66f0
musa: fix build warnings (unused variable) (#14561)
|
6 ay önce |
|
Sigbjørn Skjæret
|
e1a7059053
llama : fix incorrect minicpm3 v_states shape (#14571)
|
6 ay önce |
