 l3utterfly
|
7233358d29
memory : handle saving/loading null layers in recurrent memory (#14675)
|
6 сар өмнө |
 lixing-star
|
6c88b3bb25
ggml: fix loongarch quantize_row_q8_1 error (#14827)
|
6 сар өмнө |
 chen fan
|
14c28dfc50
CANN: weight format to NZ for Ascend310P3 (#14407)
|
6 сар өмнө |
 Aman Gupta
|
8c988fa41d
CUDA: add fused rms norm (#14800)
|
6 сар өмнө |
 Csaba Kecskemeti
|
acd6cb1c41
ggml : model card yaml tab->2xspace (#14819)
|
6 сар өмнө |
 Jeff Bolz
|
84712b6043
vulkan: fix rms_norm_mul to handle broadcasting dim0 (#14817)
|
6 сар өмнө |
 Molly Sophia
|
d4d1522b20
llama : add model type detection for rwkv7 7B&14B (#14816)
|
6 сар өмнө |
 Ed Addario
|
d1aa0cc5d1
imatrix: add option to display importance score statistics for a given imatrix file (#12718)
|
6 сар өмнө |
 stduhpf
|
c8ade30036
Mtmd: add a way to select device for vision encoder (#14236)
|
6 сар өмнө |
 Sigbjørn Skjæret
|
e28c0b80c2
cuda : implement bf16 cpy ops and enable bf16 cont (#14763)
|
6 сар өмнө |
 lhez
|
8e6f8bc875
opencl: remove unreachable `return` (#14806)
|
6 сар өмнө |
|
Molly Sophia
|
adef81781a
server : allow setting `--reverse-prompt` arg (#14799)
|
6 сар өмнө |
 R0CKSTAR
|
48b86c4fdb
cuda: remove linking to cublasLt (#14790)
|
6 сар өмнө |
|
Sigbjørn Skjæret
|
38d3af1b73
opencl: fix `im2col` when `KW!=KH` (#14803)
|
6 сар өмнө |
 rmatif
|
6c9ee3b17e
opencl: add conv2d kernel (#14403)
|
6 сар өмнө |
 Romain Biessy
|
cd465d823c
sycl: Fix im2col (#14797)
|
6 сар өмнө |
 Charles Xu
|
922042601b
kleidiai: add support for get_rows (#14676)
|
6 сар өмнө |
 Radoslav Gerganov
|
2ba1333b35
docs : fix backends table in README.md (#14796)
|
6 сар өмнө |
|
Jeff Bolz
|
c2e058f1b4
vulkan/cuda: Fix im2col when KW!=KH (#14789)
|
6 сар өмнө |
|
Molly Sophia
|
c82d48ec23
llama : fix `--reverse-prompt` crashing issue (#14794)
|
6 сар өмнө |
 IsaacDynamo
|
b4efd77f8a
server : add parse_special option to /tokenize endpoint (#14783)
|
6 сар өмнө |
|
Aman Gupta
|
2be60cbc27
docs : fix link for tools/perplexity in README.md (#14780)
|
6 сар өмнө |
 rspOverflow
|
b526ad2668
Documentation: Further revisions to the Vulkan section in build.md (#14785)
|
6 сар өмнө |
|
Aman Gupta
|
938b785764
Clang-format: local files first + fix BinPacking (#14779)
|
6 сар өмнө |
 0cc4m
|
36c153248f
Contrib: add 0cc4m as codeowner for Vulkan backend (#14775)
|
6 сар өмнө |
 Ervin Áron Tasnádi
|
a979ca22db
ggml: adds CONV_2D op and direct GEMM Vulkan implementation (#14316)
|
6 сар өмнө |
 compilade
|
90083283ec
imatrix : use GGUF to store importance matrices (#9400)
|
6 сар өмнө |
 Peter0x44
|
d4b91ea7b2
vulkan: Add logging for bf16 features to ggml_vk_print_gpu_info (#13274) (#14707)
|
6 сар өмнө |
|
0cc4m
|
83f5872404
Vulkan: Fix fprintf format-security warning (#14770)
|
6 сар өмнө |
|
rspOverflow
|
f0d4d176df
Documentation: Update build.md's Vulkan section (#14736)
|
6 сар өмнө |
