sync : ggml#3272

Merged

ggerganov merged 19 commits intomasterfrom

sync-ggml-25-06-20

Jun 21, 2025

Commits on Jun 20, 2025

Add `ggml_roll` (ggml/1274)

Acly
authored and
ggerganov
committed
ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258)

chaxu01
authored and
ggerganov
committed
ggml-cpu: fix uncaught underscore terminators (llama/14023)

taronaeo
authored and
ggerganov
committed
ggml-cpu: reduce asm calls for hsum (llama/14037)

taronaeo
authored and
ggerganov
committed
metal : add mean kernel (llama/14267)
ggerganov
committed
Vulkan: Set device max size for host memory to avoid OOM warning and fallback to CPU buffer (llama/14249)

0cc4m
authored and
ggerganov
committed
llamafile : support s390x SIMD instruction set (llama/14273)

taronaeo
authored and
ggerganov
committed
sycl: Cleanup codepaths in Get Rows in sycl backend (llama/14215)

ShanoToni
authored and
ggerganov
committed
build : suppress gcc15 compile warnings (llama/14261)

fanyang89
authored and
ggerganov
committed
ggml-cpu : remove unnecesary arm feature detection (llama/14281)

slaren
authored and
ggerganov
committed
CUDA: add conv_2d_dw (llama/14265)

am17an
authored and
ggerganov
committed
ggml: Update KleidiAI to v1.9.0 (llama/14277)

chaxu01
authored and
ggerganov
committed
ggml : fix repack work size for mul_mat_id (llama/14292)
ggerganov
committed
cuda : synchronize graph capture and cublas handle destruction (llama/14288)

slaren
authored and
ggerganov
committed
Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286)

authored and
ggerganov
committed
sycl: add usage of enqueue_functions extension (llama/14244)

s-Nick
authored and
ggerganov
committed
CUDA: add conv_2d_transpose (llama/14287)

am17an
authored and
ggerganov
committed
sync : ggml
ggerganov
committed
talk-llama : sync llama.cpp
ggerganov
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

sync : ggml#3272

sync : ggml#3272
ggerganov merged 19 commits intomasterfrom
sync-ggml-25-06-20

Commits on Jun 20, 2025

Add `ggml_roll` (ggml/1274)

ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258)

ggml-cpu: fix uncaught underscore terminators (llama/14023)

ggml-cpu: reduce asm calls for hsum (llama/14037)

metal : add mean kernel (llama/14267)

Vulkan: Set device max size for host memory to avoid OOM warning and fallback to CPU buffer (llama/14249)

llamafile : support s390x SIMD instruction set (llama/14273)

sycl: Cleanup codepaths in Get Rows in sycl backend (llama/14215)

build : suppress gcc15 compile warnings (llama/14261)

ggml-cpu : remove unnecesary arm feature detection (llama/14281)

CUDA: add conv_2d_dw (llama/14265)

ggml: Update KleidiAI to v1.9.0 (llama/14277)

ggml : fix repack work size for mul_mat_id (llama/14292)

cuda : synchronize graph capture and cublas handle destruction (llama/14288)

Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286)

sycl: add usage of enqueue_functions extension (llama/14244)

CUDA: add conv_2d_transpose (llama/14287)

sync : ggml

talk-llama : sync llama.cpp

sync : ggml#3272ggerganov merged 19 commits intomasterggml-org/whisper.cpp:masterfrom sync-ggml-25-06-20ggml-org/whisper.cpp:sync-ggml-25-06-20Copy head branch name to clipboard

Commits

Commits on Jun 20, 2025

sync : ggml#3272
ggerganov merged 19 commits intomasterfrom
sync-ggml-25-06-20