whisper.cpp / ggml

Commit History

CUDA: add conv_2d_transpose (llama/14287)
a728b83

am17an commited on

sycl: add usage of enqueue_functions extension (llama/14244)
2e59a96

Nicolò Scipione commited on

Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286)
0bcd751

Christian Kastner Diego Devesa commited on

cuda : synchronize graph capture and cublas handle destruction (llama/14288)
39c4fa5

Diego Devesa commited on

ggml : fix repack work size for mul_mat_id (llama/14292)
4b0d2de

ggerganov commited on

ggml: Update KleidiAI to v1.9.0 (llama/14277)
90ccf35

Charles Xu commited on

CUDA: add conv_2d_dw (llama/14265)
5cca3ec

am17an commited on

ggml-cpu : remove unnecesary arm feature detection (llama/14281)
62cf694

Diego Devesa commited on

build : suppress gcc15 compile warnings (llama/14261)
0454008

fanyang commited on

sycl: Cleanup codepaths in Get Rows in sycl backend (llama/14215)
feee739

Anton Mitkov commited on

llamafile : support s390x SIMD instruction set (llama/14273)
26bafb6

taronaeo commited on

Vulkan: Set device max size for host memory to avoid OOM warning and fallback to CPU buffer (llama/14249)
08debcd

OccamRazor commited on

metal : add mean kernel (llama/14267)
a726ecc

ggerganov commited on

ggml-cpu: reduce asm calls for hsum (llama/14037)
17c0dfa

taronaeo commited on

ggml-cpu: fix uncaught underscore terminators (llama/14023)
c005248

taronaeo commited on

ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258)
9d1d21b

Charles Xu commited on

Add `ggml_roll` (ggml/1274)
71923e5

Acly commited on

cmake: remove shader-gen step-targets from ggml-vulkan (llama/14226)
b7a7257

bandoti commited on

ggml-cpu : remove the weak alias trick (llama/14221)
a1bcb29

xctan commited on

musa: fix build warning (unused variable) (llama/14231)
165c242

yeahdongcn commited on

llama : add thread safety test (llama/14035)
acc9311

Diego Devesa ggerganov commited on

cmake: clean up external project logic for vulkan-shaders-gen (llama/14179)
bc8b1f7

bandoti commited on

HIP: disable rocwmma on gfx12 by default until rocm 7.0 (llama/14202)
f95736f

uvos commited on

ggml: Add Android support for GGML_CPU_ALL_VARIANTS (llama/14206)
7ddd89c

Charles Xu commited on

vulkan: mutex around vkQueueSubmit (llama/14127)
ef3a7d0

jeffbolznv commited on

ggml-cpu : rework weak alias on apple targets (llama/14146)
de5e986

xctan commited on

CUDA/HIP: fix ssm_scan on devices where warp size is not 32 (llama/14196)
adf6b4b

uvos commited on

HIP: Replace usage of depricated preprocessor macro __AMDGCN_WAVEFRONT_SIZE__ (llama/14183)
c3467c7

uvos commited on

sycl: Adding additional cpy dbg print output (llama/14034)
6799437

Anton Mitkov commited on

SYCL: Bump oneMath commit (llama/14152)
4d12916

Ewan Crawford commited on

sycl: Remove not needed copy f16->f32 for dnnl mul mat (llama/14125)
eed049f

Anton Mitkov commited on

cmake : handle whitepsaces in path during metal build (llama/14126)
8076017

ggerganov danbev commited on

Implement GGML_CPU_ALL_VARIANTS for ARM (llama/14080)
c9cec9d

Christian Kastner commited on

vulkan: Better thread-safety for command pools/buffers (llama/14116)
fdc26e7

jeffbolznv commited on

vulkan: Track descriptor pools/sets per-context (llama/14109)
855a3bf

jeffbolznv commited on

opencl: add `mul_mv_id_q4_0_f32_8x_flat` (llama/14003)
d0a458b

lhez commited on

Vulkan: Don't default to CPU device (like llvmpipe), even if no other device is available, to allow fallback to CPU backend (llama/14099)
dcb106f

OccamRazor commited on

rpc : nicer error messages for RPC server crash (llama/14076)
5d5056e

mcfadyeni commited on

ggml : disable warnings for tests when using MSVC (ggml/1273)
1669c07

danbev commited on

ggml : remove unused ggml_context_container (ggml/1272)
e6d6988

danbev commited on

examples : include examples in msvc disable warn (ggml/1270)
0c191be

danbev commited on

ggml : fix weak alias win32 (#0)
d47070d

ggerganov commited on

files : remove old sources (part 2)
c1c9908

ggerganov commited on

files : remove old sources
e4ae8c6

ggerganov commited on

metal : use less stack memory in FA kernel (llama/14088)
014afb6

ggerganov commited on

ggml-cpu : split arch-specific implementations (llama/13892)
8c833e9

xctan ggerganov commited on

cuda : fix device sync on buffer clear (llama/14033)
8f2e8d6

Diego Devesa commited on

CANN: Simplify the environment variable setting(#13104)
f1535d7

dou112 commited on

sycl: Add reorder to Q6_K mmvq implementation (llama/13885)
56f0e48

Nicolò Scipione commited on

cuda : fix buffer type check with integrated GPUs (llama/14069)
747ad97

Diego Devesa commited on