Commit History

sync : ggml
7d38d31

ggerganov commited on

vulkan : add fp16 support for the conv_2d kernel (llama/14872)
48e92ad

Erik Scholz commited on

vulkan: skip empty set_rows to avoid invalid API usage (llama/14860)
22fb24a

jeffbolznv commited on

HIP: Enable Matrix cores for MMQ Kernels, Enable stream-K for CDNA 3 (llama/14624)
5422b31

deepsek commited on

CANN: Implement GLU ops (llama/14884)
851010b

hipudding commited on

musa: fix build warnings (unused variable) (llama/14869)
f38d409

yeahdongcn commited on

ggml-cpu : disable GGML_NNPA by default due to instability (llama/14880)
cac085c

taronaeo commited on

opencl: add fused `rms_norm_mul` (llama/14841)
5629961

lhez commited on

ggml : remove invalid portPos specifiers from dot files (llama/14838)
a91e2f3

ORippler commited on

rpc : check for null buffers in get/set/copy tensor endpoints (llama/14868)
9a5c3ef

ChrisRohlf commited on

sched : fix multiple evaluations of the same graph with pipeline parallelism (llama/14855)
e9f5612

Diego Devesa commited on

musa: upgrade musa sdk to rc4.2.0 (llama/14498)
a687ec3

yeahdongcn commited on

cmake : Indent ggml-config.cmake (ggml/1310)
6bdff5c

Kai Pastor commited on

sycl: fixed semantics of block offset calculation (llama/14814)
d3d52a4

Alberto Cabrera Pérez commited on

metal : fix fusion across different encoders (llama/14849)
17d67da

ggerganov commited on

sycl: fix undefined variable in work group size check (llama/14843)
bcbbf47

Donghyeon Jeong commited on

CUDA: fix overflow in FA, tune performance (llama/14840)
10ac92f

JohannesGaessler commited on

CUDA: fix compilation with GGML_CUDA_F16 (llama/14837)
2746afd

JohannesGaessler commited on

ggml: fix loongarch quantize_row_q8_1 error (llama/14827)
0bd2be3

lixing-star commited on

CANN: weight format to NZ for Ascend310P3 (llama/14407)
0274100

chen fan commited on

CUDA: add fused rms norm (llama/14800)
79bc58c

am17an commited on

vulkan: fix rms_norm_mul to handle broadcasting dim0 (llama/14817)
0c16b60

jeffbolznv commited on

cuda : implement bf16 cpy ops and enable bf16 cont (llama/14763)
b54b644

Sigbjørn Skjæret commited on

opencl: remove unreachable `return` (llama/14806)
cfa3731

lhez commited on

cuda: remove linking to cublasLt (llama/14790)
fafaa8b

yeahdongcn commited on

opencl: fix `im2col` when `KW!=KH` (llama/14803)
2fdd2df

Sigbjørn Skjæret commited on

opencl: add conv2d kernel (llama/14403)
d579f20

mrfatso commited on

sycl: Fix im2col (llama/14797)
931edc1

Romain Biessy commited on

kleidiai: add support for get_rows (llama/14676)
43ba97c

Charles Xu commited on

vulkan/cuda: Fix im2col when KW!=KH (llama/14789)
0be0329

jeffbolznv commited on

ggml: adds CONV_2D op and direct GEMM Vulkan implementation (llama/14316)
5885084

etasnadi commited on

vulkan: Add logging for bf16 features to ggml_vk_print_gpu_info (#13274) (llama/14707)
0855a18

Peter0x44 commited on

Vulkan: Fix fprintf format-security warning (llama/14770)
77a1c11

OccamRazor commited on

cmake : fix usage issues (ggml/1257)
c38df55

Kai Pastor commited on

ggml-cpu : remove stdlib include from repack.cpp (ggml/1276)
91c01e9

danbev commited on

Support static xcframework packaging in build-xcframework.sh (#3322)
78de49d
unverified

Rich Waters danbev commited on

examples : add note about WHISPER_WASM_SINGLE_FILE [no ci] (#3332)
4a1f367
unverified

danbev commited on

ci : add paths to build.yml (#3333)
6437539
unverified

danbev commited on

musa: upgrade musa sdk to rc4.2.0 (#3324)
50c5b9e
unverified

R0CKSTAR commited on

server : hide language probabilities option behind flag (#3328)
606bf70
unverified

sachaarbonel commited on

go: fix Mac OS X builds (#3310)
2fd8067
unverified

BVK Chaitanya Chaitanya Bayapuneni commited on

sync : ggml
ebe9052

ggerganov commited on

metal : fuse add, mul + add tests (llama/14596)
66ae493

ggerganov commited on

cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (llama/14741)
bb523fb

Oliver Simons commited on

CUDA: set_rows + cpy.cu refactor (llama/14712)
536128f

am17an commited on

use max work group size for device to replace the magic number (llama/14732)
e5e9b79

Neo Zhang Jianyu commited on

ggml: Add initial WebGPU backend (llama/14521)
0dd208f

Reese Levine commited on