whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml.h

Commit History

ggml : sync latest ggml repo

6ee8740
unverified

ggerganov HF Staff commited on May 20, 2023

ggml : sync latest ggml

803e1be
unverified

ggerganov HF Staff commited on May 14, 2023

ggml : sync ggml (clBLAST + tensor names)

f50d3b3
unverified

ggerganov HF Staff commited on May 2, 2023

whisper : add integer quantization support (#540)

a5f8f3c
unverified

ggerganov HF Staff commited on Apr 30, 2023

ggml : sync with ggml repo (warning fixes + asserts)

caf2759
unverified

ggerganov HF Staff commited on Apr 29, 2023

ggml : sync latest ggml + llama.cpp updates (quantization)

ede1268
unverified

ggerganov HF Staff commited on Apr 29, 2023

ggml : sync latest ggml

7b8292f
unverified

ggerganov HF Staff commited on Apr 14, 2023

ggml : sync latest changes from ggml and llama.cpp

3bd52ce
unverified

ggerganov HF Staff commited on Apr 13, 2023

ggml : backport llama.cpp updates (close #709)

bf6b4f8
unverified

ggerganov HF Staff commited on Apr 10, 2023

talk-llama : add new example + sync ggml from llama.cpp (#664)

a8c74e6
unverified

ggerganov HF Staff commited on Mar 27, 2023

whisper : reduce memory usage during inference (#431)

3aa9e6c
unverified

ggerganov HF Staff commited on Feb 4, 2023

ggml : add SSE3 and fp16 conversion lookup table (#368)

2c3f7d4
unverified

Abitofevrything

ggerganov HF Staff commited on Jan 6, 2023

whisper : document POWER VSX support

4dbf7ee

Thomas Fitzsimmons commited on Jan 5, 2023

ggml : simplify the SIMD code (#324)

6fe850c
unverified

ggerganov HF Staff commited on Dec 24, 2022

Check for both __ARM_NEON and __ARM_FEATURE_FMA so that the project can be compiled for armv7a.

1fff54f

Kevin Brothaler commited on Dec 20, 2022

ggml : make more compatible with c99 (#262)

52bc68d
unverified

ggerganov HF Staff commited on Dec 16, 2022

ggml : add F16C CPU flag check

2661c19
unverified

ggerganov HF Staff commited on Dec 6, 2022

add AVX support

00ac035

katsu560 commited on Nov 23, 2022

ref #40 : start working on the documentation

7ef045e
unverified

ggerganov HF Staff commited on Nov 9, 2022

parallel : working

d5d2d41

ggerganov HF Staff commited on Oct 29, 2022

ggml : add system info functions

7a4a7a1

ggerganov HF Staff commited on Oct 25, 2022

Building with MSVC

5ca6886

stanimirovb commited on Oct 11, 2022

wip : rpi4 support

b69a5a5

ggerganov HF Staff commited on Oct 5, 2022

Flash + language support (ref #2)

dd296e7
unverified

ggerganov HF Staff commited on Sep 28, 2022

Initial release

f9c5a09
unverified

ggerganov HF Staff commited on Sep 25, 2022

Commit History

ggml : sync latest ggml repo 6ee8740 unverified

ggml : sync latest ggml 803e1be unverified

ggml : sync ggml (clBLAST + tensor names) f50d3b3 unverified

whisper : add integer quantization support (#540) a5f8f3c unverified

ggml : sync with ggml repo (warning fixes + asserts) caf2759 unverified

ggml : sync latest ggml + llama.cpp updates (quantization) ede1268 unverified

ggml : sync latest ggml 7b8292f unverified

ggml : sync latest changes from ggml and llama.cpp 3bd52ce unverified

ggml : backport llama.cpp updates (close #709) bf6b4f8 unverified

talk-llama : add new example + sync ggml from llama.cpp (#664) a8c74e6 unverified

whisper : reduce memory usage during inference (#431) 3aa9e6c unverified

ggml : add SSE3 and fp16 conversion lookup table (#368) 2c3f7d4 unverified

whisper : document POWER VSX support 4dbf7ee

ggml : simplify the SIMD code (#324) 6fe850c unverified

Check for both __ARM_NEON and __ARM_FEATURE_FMA so that the project can be compiled for armv7a. 1fff54f

ggml : make more compatible with c99 (#262) 52bc68d unverified

ggml : add F16C CPU flag check 2661c19 unverified

add AVX support 00ac035

ref #40 : start working on the documentation 7ef045e unverified

parallel : working d5d2d41

ggml : add system info functions 7a4a7a1

Building with MSVC 5ca6886

wip : rpi4 support b69a5a5

Flash + language support (ref #2) dd296e7 unverified

Initial release f9c5a09 unverified