stduhpf
|
c8ade30036
Mtmd: add a way to select device for vision encoder (#14236)
|
5 месяцев назад |
Sigbjørn Skjæret
|
e28c0b80c2
cuda : implement bf16 cpy ops and enable bf16 cont (#14763)
|
5 месяцев назад |
lhez
|
8e6f8bc875
opencl: remove unreachable `return` (#14806)
|
5 месяцев назад |
Molly Sophia
|
adef81781a
server : allow setting `--reverse-prompt` arg (#14799)
|
6 месяцев назад |
R0CKSTAR
|
48b86c4fdb
cuda: remove linking to cublasLt (#14790)
|
6 месяцев назад |
Sigbjørn Skjæret
|
38d3af1b73
opencl: fix `im2col` when `KW!=KH` (#14803)
|
6 месяцев назад |
rmatif
|
6c9ee3b17e
opencl: add conv2d kernel (#14403)
|
6 месяцев назад |
Romain Biessy
|
cd465d823c
sycl: Fix im2col (#14797)
|
6 месяцев назад |
Charles Xu
|
922042601b
kleidiai: add support for get_rows (#14676)
|
6 месяцев назад |
Radoslav Gerganov
|
2ba1333b35
docs : fix backends table in README.md (#14796)
|
6 месяцев назад |
Jeff Bolz
|
c2e058f1b4
vulkan/cuda: Fix im2col when KW!=KH (#14789)
|
6 месяцев назад |
Molly Sophia
|
c82d48ec23
llama : fix `--reverse-prompt` crashing issue (#14794)
|
6 месяцев назад |
IsaacDynamo
|
b4efd77f8a
server : add parse_special option to /tokenize endpoint (#14783)
|
6 месяцев назад |
Aman Gupta
|
2be60cbc27
docs : fix link for tools/perplexity in README.md (#14780)
|
6 месяцев назад |
rspOverflow
|
b526ad2668
Documentation: Further revisions to the Vulkan section in build.md (#14785)
|
6 месяцев назад |
Aman Gupta
|
938b785764
Clang-format: local files first + fix BinPacking (#14779)
|
6 месяцев назад |
0cc4m
|
36c153248f
Contrib: add 0cc4m as codeowner for Vulkan backend (#14775)
|
6 месяцев назад |
Ervin Áron Tasnádi
|
a979ca22db
ggml: adds CONV_2D op and direct GEMM Vulkan implementation (#14316)
|
6 месяцев назад |
compilade
|
90083283ec
imatrix : use GGUF to store importance matrices (#9400)
|
6 месяцев назад |
Peter0x44
|
d4b91ea7b2
vulkan: Add logging for bf16 features to ggml_vk_print_gpu_info (#13274) (#14707)
|
6 месяцев назад |
0cc4m
|
83f5872404
Vulkan: Fix fprintf format-security warning (#14770)
|
6 месяцев назад |
rspOverflow
|
f0d4d176df
Documentation: Update build.md's Vulkan section (#14736)
|
6 месяцев назад |
Georgi Gerganov
|
b17230917c
sync : ggml
|
6 месяцев назад |
Georgi Gerganov
|
bf9087f59a
metal : fuse add, mul + add tests (#14596)
|
6 месяцев назад |
Georgi Gerganov
|
9fb1042ce6
graph : fix graph reuse reset of params (#14760)
|
6 месяцев назад |
Georgi Gerganov
|
2adf8d83ac
parallel : add option for different RNG seeds (#14757)
|
6 месяцев назад |
Oliver Simons
|
021cc28bef
cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (#14741)
|
6 месяцев назад |
Georgi Gerganov
|
d498af3d5a
graph : avoid huge warm-up graphs for MoE models (#14753)
|
6 месяцев назад |
Georgi Gerganov
|
eacdeb5bfc
model : fix build after merge conflict (#14754)
|
6 месяцев назад |
lgai-exaone
|
e0cb5c5cb8
model : add EXAONE 4.0 support (#14630)
|
6 месяцев назад |