 Xuan-Son Nguyen
|
84a9bf2fc2
mtmd : merge llava, gemma3 and minicpmv CLI into single `llama-mtmd-cli` (#13012)
|
9 месяцев назад |
|
Xuan-Son Nguyen
|
2016f07bd1
convert : experimental support for `--mmproj` flag (#13023)
|
9 месяцев назад |
 Jeffrey Morgan
|
6602304814
llava: fix errors in clip.h on certain compilers (#13030)
|
9 месяцев назад |
 Jeff Bolz
|
66168204be
vulkan: support noncontiguous rms_norm (#13031)
|
9 месяцев назад |
|
Jeffrey Morgan
|
4ba9d711ba
metal: add neg operator (#13029)
|
9 месяцев назад |
 bandoti
|
00137157fc
Disable CI cross-compile builds (#13022)
|
9 месяцев назад |
 Sigbjørn Skjæret
|
fb28f4f80e
gguf-py : fix upload python package workflow (#13020)
|
9 месяцев назад |
|
Xuan-Son Nguyen
|
37b9f0d29d
clip : refactor, add `image_manipulation` and `llava_uhd` classes (#13011)
|
9 месяцев назад |
 Daniel Tang
|
6408210082
main : Fix Ctrl+D/newline handling (#12951)
|
9 месяцев назад |
 Chris Thompson
|
aff9d107b0
gguf-py : GGUF Editor GUI - Python + Qt6 (#12930)
|
9 месяцев назад |
|
Xuan-Son Nguyen
|
35370ba945
server : use std::move whenever possible (#12936)
|
9 месяцев назад |
 Akarshan Biswas
|
8d66005763
SYCL: Refactor and enable FP16 in binary broadcast OPs (#12975)
|
9 месяцев назад |
|
Xuan-Son Nguyen
|
b9154ecff9
mtmd : add methods to access `mtmd_image_tokens` (#12906)
|
9 месяцев назад |
 Radoslav Gerganov
|
2db9ba1464
rpc : add RPC_CMD_HELLO (#12955)
|
9 месяцев назад |
 Georgi Gerganov
|
2f74c354c0
graph : make FA compatible with MLA + add initial Metal kernels (#12953)
|
9 месяцев назад |
 Alan Gray
|
207c22ec2d
ggml: Re-enable CUDA graphs in presence of CONT and DUP nodes (#12970)
|
9 месяцев назад |
 hipudding
|
7a395f67a7
CANN: Add support for async operator submission (#12864)
|
9 месяцев назад |
 Mikko Juola
|
971f245b3b
llama : recognize IBM Granite 3.3 FIM tokens (#12988)
|
9 месяцев назад |
 kimminsu
|
12b17501e6
opencl: fix incorrect local_size index in profiling log (#12868)
|
9 месяцев назад |
|
Jeff Bolz
|
015022bb53
vulkan: enable coopmat2 FA gqa and split_k optimizations more often (#12931)
|
9 месяцев назад |
 Chenguang Li
|
b43d89e311
CANN: Add 310P operator support check (#12962)
|
9 месяцев назад |
 lhez
|
80f19b4186
opencl: split `ggml-opencl.cl` into multiple files and cleanup (#12886)
|
9 месяцев назад |
|
Georgi Gerganov
|
f8f820cc4d
metal : add FA-vec kernels for head size 96 (#12952)
|
9 месяцев назад |
|
hipudding
|
54a7272043
CANN: Add x86 build ci (#12950)
|
9 месяцев назад |
 David Huang
|
84778e9770
CUDA/HIP: Share the same unified memory allocation logic. (#12934)
|
9 месяцев назад |
|
Akarshan Biswas
|
510676475f
SYCL: Add ROPE vision kernel (#12887)
|
9 месяцев назад |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 месяцев назад |
 Srihari-mcw
|
eccc7a1602
ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (#12829)
|
9 месяцев назад |
|
Chenguang Li
|
0019279bb5
CANN: Opt ROPE optimization (#12865)
|
9 месяцев назад |
 Xinpeng Dou
|
b0c75ac9f9
CANN: Optimize CANN buffer pool memory management (#12875)
|
9 месяцев назад |
