e2aa556a99
whisper : experiments with Flash Attention in the decoder
1 year ago
f30b5d322c
ggml : fix bug in new soft max computation
1 year ago
44efbf7ff1
cmake : add -Wno-unused-function + update whisper.js
1 year ago
d347a59a5f
ggml : when using BLAS start only 1 CPU thread
1 year ago
6394c906af
ggml : fix running tasks with variable number of threads
1 year ago
74ffa14e1d
ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16
1 year ago
65fdcbbbbb
whisper : revert accidental MB change
1 year ago
d61d55cd4b
ggml : speed-up soft max via Accelerate + unroll
1 year ago
d51fc3ee0a
ggml : use vDSP_sve and vDSP_maxv from Accelerate
1 year ago
f82a7dd019
ggml : make gcc happy (minor)
1 year ago
87dd4a3081
talk.wasm : bump memory usage + update whisper.js
1 year ago
41e05c6b1b
cmake : support AVX2 in Windows better ( #381 )
1 year ago
fa379cb22a
Revert "tmp"
...
This reverts commit 1652965529
1 year ago
322f4e6c4e
go : bindings updated so they can be used in third party packages. ( #379 )
...
* Updated bindings so they can be used in third pary packages.
* Updated makefiles to set FMA flag on optionally, for xeon E5 on Darwin
1 year ago
1652965529
tmp
1 year ago
6042c7a3be
cmake : change min required version to 3.0 ( #351 )
...
We increase the min version only when want to use particular
functionality that is available in the newer version
1 year ago
6b351bb669
command : add "guided-mode" video demo in the README.md
1 year ago
a62170c656
ggml : add SSE3 and fp16 conversion lookup table ( #368 )
...
* Improves WASM performance:
On MacBook M1 Pro, I observe 25% faster using Firefox and 35% faster using Chrome
* Add support for SSE3 SIMD
* Add SSE3 to system information
* Add Imath support for fp16-fp32 conversions
* Add Imath to system information
* Wrap Imath calls to avoid static function warnings
* Drop Imath; Add lookup table for f16 -> f32 conversions
* Remove TODO comments
* Update SSE3 to new macro arguments
* Correct updated macro definitions
* Prefer static inline where possible
* ggml : static inlines + add public f16 <-> f32 conversions
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
1944e7c33e
whisper : document POWER VSX support
2 years ago
49a8dd6732
ggml : reorganize POWER9 ppc64le SIMD code
2 years ago
8c7f642286
ggml : change f16 load and store macro arguments
2 years ago
ad2a4ffa03
whisper : do not use F16 tensors when in F32 mode ( #369 )
2 years ago
b3c865083e
ci : add emscripten build
2 years ago
a0d4f8e65c
main : make whisper_print_segment_callback() more readable ( close #371 )
2 years ago
4a214d2f07
cmake : add CMAKE_RUNTIME_OUTPUT_DIRECTORY
...
Currently needed by the wasm examples
2 years ago
0a0cfa7985
ggml : add void to argument-less functions
2 years ago
196d738974
minor : close #370 + Makefile build info print change
2 years ago
84c6b42e65
cmake : update to 3.19 ( #351 )
...
- update from 3.0 (from 2014) to 3.19 (from 2020)
- move some global setting onto the targets (through a cmake include)
2 years ago
dd6d582977
whisper : use ranged-based for loops for readability
2 years ago
d51c5eb906
ggml : define MIN / MAX only if not defined (minor)
2 years ago
0be6a1afd9
make : print build information
2 years ago
a466c3404d
stream : fix data race on bool + avoid division-by-zero
2 years ago
d629c034a4
models : fix HF model URL ( close #356 )
2 years ago
f00509d57c
command : refactor to split command list & general transcription modes ( #331 )
...
This makes it easier to understand if you're looking for only one of the capabilities.
2 years ago
424c410c42
ggml : improve f16 acceleration for POWER9 ppc64le
2 years ago
d97e6005e9
whisper : add whisper_n_audio_ctx and check for invalid audio_ctx
...
closes #344
2 years ago
3467230a77
models : fix typo in convert-h5-to-ggml.py
...
signficant -> significant
2 years ago
a091581eb3
cmake : add runtime destination install ( #345 )
...
needed for mingw32 build to successfully install the dlls in the correct location
2 years ago
68daf6e487
whisper : avoid some memory allocations
2 years ago
a593b932e4
main : add -ocsv, aka --output-csv to output a CSV file
...
Adds -ocsv, aka --output-csv feature to examples/main, which outputs a CSV file containing lines formatted as follows <startTime-in-integer-milliseconds>, <endTime-in-integer-milliseconds>, "<transcript-line-including-commas>".
2 years ago
9a8ad3db69
make : add i686 arch ( close #329 )
2 years ago
4e0b2069e7
ggml : barrier refactor + static functions
2 years ago
ac521a566e
ggml : simplify the SIMD code ( #324 )
...
* ggml : simplify the SIMD code
* ggml : generic reduce for all register sizes + comments
2 years ago
331c0bbddc
examples : fix memory leak on failure to load gpt2 model ( #323 )
2 years ago
dc90efd504
examples : small code cleanups ( #322 )
...
- remove unnecessary initialization of string to ""
- use empty() instead of checking size()
- use emplace_back instead of push_back
- use nullptr instead of NULL
- remove unnecessary call to .data() on string
- use character overload of find_first_of() instead of passing a string
2 years ago
7282e2109e
ggml : use vaddvq_f32 for slightly more efficient reduce
2 years ago
466ceebb78
ggml : add f16 acceleration for POWER9 ppc64le
2 years ago
77226aa89d
models : fix support for spaces in path ( close #315 )
2 years ago
543bd5627e
whisper : use emplace_back in place of push_back ( #319 )
...
This avoids potential construction of temporaries.
2 years ago
62fee9a9cc
whisper : fix mem leak on failure to load model ( #318 )
2 years ago
Georgi Gerganov
m.bell
David Thorpe
Abitofevrything
Thomas Fitzsimmons
Andy Maloney
Ikko Ashimine
Avik Sengupta
Niels Mayer