Commits · Xenobd/whisper.cpp

ngxson HF Staff slaren commited on Aug 5

ggerganov commited on Jul 18

jeffbolznv slaren commited on Jun 29

taronaeo slaren commited on Jun 25

Daniel Tang commited on May 28

xctan commited on May 27

Piotr Kubaj commited on Apr 9

cmdr2 commited on Apr 10

Diego Devesa commited on Apr 9

ggerganov commited on Apr 7

ggerganov commited on Mar 27

Bodhi Bodhi Hu commited on Feb 21

JohannesGaessler commited on Dec 17, 2024

Diego Devesa commited on Dec 12, 2024

Frankie Robertson commited on Dec 4, 2024

Diego Devesa commited on Dec 3, 2024

Frankie Robertson commited on Nov 26, 2024

JohannesGaessler commited on Nov 20, 2024

JohannesGaessler commited on Nov 16, 2024

Diego Devesa

ggerganov R0CKSTAR commited on Nov 14, 2024

Diego Devesa commited on Nov 3, 2024

Gilad S commited on Oct 16, 2024

Diego Devesa commited on Oct 3, 2024

ggerganov commited on Sep 20, 2024

compilade commited on Sep 6, 2024

jdomke domke commited on Aug 3, 2024

Sigbjørn Skjæret

compilade commited on Aug 2, 2024

slaren commited on Jul 27, 2024

Dibakar Gope commited on Jul 10, 2024

ggerganov commited on Jun 26, 2024

Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

Commit History

Commit History

llama : add gpt-oss (llama/15091) bf225d6

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

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 737f12d

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) fea8f94

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 1459465

ggml : riscv: add xtheadvector support (llama/13720) 4790d5d

ggml-impl.h: fix build on POWER9 (llama/12855) 3a1d5ca

ggml: don't include arm_neon.h when using CUDA 12 with ARM Neon (ggml/1187) 87f1ea3

ggml : add more generic custom op, remove deprecated custom ops (ggml/1183) ba7a5f8

ggml : simplify Arm fp16 CPU logic (ggml/1177) fb13b88

ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0) f695cbf

MUSA: support ARM64 and enable dp4a .etc (llama/11843) ab96dac

GGUF: C++ refactor, backend support, misc fixes (llama/11030) 21c5b64

tests: add tests for GGUF (llama/10830) e7722cb

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) b38cecf

Avoid using __fp16 on ARM with old nvcc (llama/10616) 19743b6

ggml : move AMX to the CPU backend (llama/10570) 3732429

Do not include arm_neon.h when compiling CUDA code (ggml/1028) 80663f4

ggml-opt: fix data corruption (ggml/1022) a916e92

ggml: new optimization interface (ggml/988) dd33ace

ggml : build backends as libraries (llama/10256) 3dc93f3

ggml : move CPU backend to a separate file (llama/10144) 0f447f2

fix: use `vm_allocate` to allocate CPU backend buffer on macOS (llama/9875) cf75979

ggml-backend : add device and backend reg interfaces (llama/9707) 9d74d85

ggml : refactoring (llama/#0) 1b62c96

ggml-quants : ternary packing for TriLMs and BitNet b1.58 (llama/8151) d1c244a

ggml : reading the runtime sve config of the cpu (llama/8709) c26339f

Fix conversion of unnormalized BF16->BF16 weights (llama/7843) 8b10f59

ggml : reduce hash table reset cost (llama/8698) 9808fbf

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780) 9509586

whisper : reorganize source code + improve CMake (#2256) f75c2e3 unverified

llama : add gpt-oss (llama/15091)

bf225d6

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

66ae493

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366)

737f12d

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317)

fea8f94

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

1459465

ggml : riscv: add xtheadvector support (llama/13720)

4790d5d

ggml-impl.h: fix build on POWER9 (llama/12855)

3a1d5ca

ggml: don't include arm_neon.h when using CUDA 12 with ARM Neon (ggml/1187)

87f1ea3

ggml : add more generic custom op, remove deprecated custom ops (ggml/1183)

ba7a5f8

ggml : simplify Arm fp16 CPU logic (ggml/1177)

fb13b88

ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0)

f695cbf

MUSA: support ARM64 and enable dp4a .etc (llama/11843)

ab96dac

GGUF: C++ refactor, backend support, misc fixes (llama/11030)

21c5b64

tests: add tests for GGUF (llama/10830)

e7722cb

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)

b38cecf

Avoid using __fp16 on ARM with old nvcc (llama/10616)

19743b6

ggml : move AMX to the CPU backend (llama/10570)

3732429

Do not include arm_neon.h when compiling CUDA code (ggml/1028)

80663f4

ggml-opt: fix data corruption (ggml/1022)

a916e92

ggml: new optimization interface (ggml/988)

dd33ace

ggml : build backends as libraries (llama/10256)

3dc93f3

ggml : move CPU backend to a separate file (llama/10144)

0f447f2

fix: use `vm_allocate` to allocate CPU backend buffer on macOS (llama/9875)

cf75979

ggml-backend : add device and backend reg interfaces (llama/9707)

9d74d85

ggml : refactoring (llama/#0)

1b62c96

ggml-quants : ternary packing for TriLMs and BitNet b1.58 (llama/8151)

d1c244a

ggml : reading the runtime sve config of the cpu (llama/8709)

c26339f

Fix conversion of unnormalized BF16->BF16 weights (llama/7843)

8b10f59

ggml : reduce hash table reset cost (llama/8698)

9808fbf

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780)

9509586

whisper : reorganize source code + improve CMake (#2256)

f75c2e3
unverified