ggerganov/whisper.cpp

Pull Requests Commits

cmake : fix android build (#3265)

ggerganov committed 198 days ago

Verified 17bece18

examples : add stereo to mono conversion in read_audio_data (#3266)

danbev committed 199 days ago

Verified ecb8f3c2

talk-llama : sync llama.cpp

ggerganov committed 199 days ago

2f60ebc3

ggerganov committed 199 days ago

69061e35

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

bandoti committed 199 days ago

0e068779

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

xctan committed 199 days ago

ac8a303c

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

yeahdongcn committed 199 days ago

2a845939

llama : add thread safety test (llama/14035)

slaren committed 199 days ago

44871c8a

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

bandoti committed 199 days ago

ad6cd94a

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

IMbackK committed 199 days ago

dbad9d8f

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

chaxu01 committed 199 days ago

518835ee

vulkan: mutex around vkQueueSubmit (llama/14127)

jeffbolznv committed 199 days ago

a3d1c55c

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

xctan committed 199 days ago

0c25129d

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

IMbackK committed 199 days ago

a433680a

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

IMbackK committed 199 days ago

aeaed980

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

ShanoToni committed 199 days ago

4ea599af

SYCL: Bump oneMath commit (llama/14152)

Ewan Crawford committed 199 days ago

783cf030

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

ShanoToni committed 199 days ago

0097eaf8

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

ggerganov committed 199 days ago

a96a880f

Implement GGML_CPU_ALL_VARIANTS for ARM (llama/14080)

ckastner committed 199 days ago

26c16ad6

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

jeffbolznv committed 199 days ago

40d0d47c

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

jeffbolznv committed 199 days ago

40c65255

opencl: add `mul_mv_id_q4_0_f32_8x_flat` (llama/14003)

lhez committed 199 days ago

74c68067

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

0cc4m committed 199 days ago

794bf239

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

isaac-mcfadyen committed 199 days ago

26dcc196

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

danbev committed 199 days ago

ffe5400d

ggml : remove unused ggml_context_container (ggml/1272)

danbev committed 199 days ago

1b01c0cc

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

danbev committed 199 days ago

db30f467

whisper : clear result_all if vad_samples is empty (#3262)

danbev committed 199 days ago

Verified 1591558c

examples : set the C++ standard to C++17 for server (#3261)

danbev committed 200 days ago

Verified f3ff80ea

Newer Older