Spaces:

natasa365
/

whisper.cpp

Sleeping

App Files Files Community

whisper.cpp / ggml /src /ggml-cpu /vec.h

Commit History

llama : add gpt-oss (llama/15091)

bf225d6

ggerganov

ngxson HF Staff slaren commited on Aug 5

ggml : add ggml_scale_bias (llama/14417)

573d50a

ngxson HF Staff commited on Jul 9

ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445)

f798922

Sigbjørn Skjæret commited on Jul 3

llama : initial Mamba-2 support (llama/9126)

1b4087e

compilade commited on Jul 2

ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring (llama/14443)

f7995cb

Sigbjørn Skjæret commited on Jun 29

ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158)

add5c0f

Sigbjørn Skjæret

ggerganov

OccamRazor Akarshan

jeffbolznv commited on Jun 29

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

fea8f94

taronaeo slaren commited on Jun 25

ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (llama/13882)

bfc960a

Vineel Abhinav

ggerganov commited on May 29

ggml: aarch64: Implement SVE F32 kernels for vector functions (llama/13843)

7941e9b

Vineel Abhinav commited on May 29

ggml : add ggml_gelu_erf() (llama/13667)

6c9cd9a

ngxson HF Staff commited on May 21

cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167)

0754d43

cmdr2 Diego Devesa commited on Apr 2

Commit History

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

ggml : add ggml_scale_bias (llama/14417) 573d50a

ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445) f798922

llama : initial Mamba-2 support (llama/9126) 1b4087e

ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring (llama/14443) f7995cb

ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) add5c0f

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

ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (llama/13882) bfc960a

ggml: aarch64: Implement SVE F32 kernels for vector functions (llama/13843) 7941e9b

ggml : add ggml_gelu_erf() (llama/13667) 6c9cd9a

cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167) 0754d43