Spaces:
Sleeping
Sleeping
Commit History
-
examples : command.wasm updates (#2904)
Unverified signatureThis commit updates the command.wasm example by adding a server.py script to make it easy to start a local http server to try out the example, updates the build instructions, and also addresses some of the compiler warnings that were being generated. * emscripten : fix TOTAL_STACK for wasm This commit moves the TOTAL_STACK setting from the compile flags to the linker flags. This is because the TOTAL_STACK setting is a linker setting. The motivation for this change is that currently the following warnings are generated when building: ```console em++: warning: linker setting ignored during compilation: 'TOTAL_STACK' [-Wunused-command-line-argument] em++: warning: linker setting ignored during compilation: 'TOTAL_STACK' [-Wunused-command-line-argument] em++: warning: linker setting ignored during compilation: 'TOTAL_STACK' [-Wunused-command-line-argument] em++: warning: linker setting ignored during compilation: 'TOTAL_STACK' [-Wunused-command-line-argument] em++: warning: linker setti…0db3249
-
whisper : add option to use system-installed GGML (#2887)
PeterUnverified signaturece83587
-
release : v1.7.4
Unverified signaturec775ca4
-
release : v1.7.3
Unverified signature50c0d82
-
release : v1.7.2
Unverified signature414329d
-
release : v1.7.1
Unverified signature1b81cb9
-
release : v1.7.0
Unverified signature5abc285
-
revert : cmake : set MSVC to use UTF-8 on source files (#2346)
This reverts commit c96906d84dd6a1c40ea797ad542df3a0c47307a3.5e9ff52
-
cmake : set MSVC to use UTF-8 on source files (#2346)
Tim MillerUnverified signature9b3df8e
-
cmake : allow external ggml
e6c1269 -
cmake : remove install of llama convert script [no ci] (#2266)
f73ff9a
-
whisper : reorganize source code + improve CMake (#2256)
Unverified signature* scripts : update sync [no ci] * files : reorganize [no ci] * sync : llama.cpp * cmake : link math library * cmake : build normal ggml library * files : move headers to include * objc : fix path to ggml-metal.h * ci : fix WHISPER_CUDA -> GGML_CUDA * scripts : sync LICENSE [no ci]f75c2e3
-
build : update make / cmake
0b4241c -
cmake : fix sycl build (#0)
9a475af -
ggml : remove OpenCL (#0)
d303fe3 -
cuda : enable CUDA graphs (#0)
d075551 -
cmake : fix CUDA build (#0)
ddc04a3
-
whisper : add CUDA-specific computation mel spectrograms (#2206)
Unverified signature* whisper : use polymorphic class to calculate mel spectrogram * whisper : add cuda-specific mel spectrogram calculation * whisper : conditionally compile cufftGetErrorString to avoid warnings * build : add new files to makefile * ruby : add new files to conf script * build : fix typo in makefile * whisper : suppress cub warning for deprecated C++ std in whisper-mel-cudac6894d3
-
release : v1.6.2
Unverified signature3e54141
-
release : v1.6.1
Unverified signatureca6f4b2 -
examples : add support for decoding input with ffmpeg (Linux) (#2133)
William TambelliniUnverified signature- search for ffmpeg libs/headers at cmake time - added ffmpeg-transcode.cpp into libcommon if ffmpeg on - hooked ffmpeg trancoding in common read_wav(...) - passed test: ./main -m ggml-base.en.bin -f samples/jfk.mp3c160b58
-
release : v1.6.0
Unverified signatured823237
-
cmake : fix HIP/ROCm build (#2102)
aldorofUnverified signaturea90ae59 -
cmake : fix metal embed sources path (#2110)
Unverified signature087b1a8
-
build : improve disabling AVX-512 (#2129)
Przemysław PawełczykUnverified signature* cmake : make WHISPER_NO_AVX512=ON disable all subsets of AVX-512 Previously it happened only for MSVC, but it makes sense to have the same behavior for other compilers too. * make : reorder x86 ISA extensions in chronological order And update compiler flags at the end to ease modifying conditions. * make : support WHISPER_NO_AVX512=1 for disabling all AVX-512 subsets. That way you do not have to override each AVX-512 subset setting individually if it has been turned on during autodetection.dd6f1ab
-
release : v1.5.5
Unverified signature460bd9e
-
build : fix embedded Metal library generation (#2045)
Didzis GoskoUnverified signatureb0e83a9 -
build : detect AVX512 in Makefile, add AVX512 option in CMake (#2043)
Didzis GoskoUnverified signature* make : add AVX512 detection to Makefile and CMakeLists.txt * make : autodetect more AVX512 instruction subsets * cmake : do not default to AVX512, must be enabled explicitly * cmake : enable a set of AVX512 subsets, when AVX512 is turned on * make : consolidate AVX512 subsets, add AVX512 VBMI * cmake : revert to NO AVX512 setting, add settings for AVX512 VNNI and VBMI * make : re-introduce AVX512VNNI back * cmake : remove superfluous comment line9d0bb12
-
cmake : support for CPU BLAS build via Intel MKL (#2024)
slashlibUnverified signature9a2c42b -
cmake : create solution folders (#2004)
ulatekhUnverified signature* Create solution folders in the CMake build. * Fixed non-SDL2 build. * Fixed emscripten build.2616a7c
-
build : use pkg-config for OpenBLAS (#1778)
Przemysław PawełczykUnverified signature* make : use pkg-config for finding CFLAGS & LDFLAGS needed by OpenBLAS That way building on *nix like environments (including MSYS2 on Windows) with WHISPER_OPENBLAS=1 works out of the box. Fix handling of WHISPER_OPENBLAS, so that empty value or 0 won't be misinterpreted by make as enabled. Mind that it's not intended to detect CMake false constants (OFF NO FALSE N). make is not CMake. By default OpenBLAS with 64-bit interface is used, but that can be changed with `WHISPER_OPENBLAS_INTERFACE64=0` if 32-bit one is desired. If OpenBLAS headers and library are respectively in include/ and lib/ subdirectories of given path, then you can specify it, e.g. `OPENBLAS_PATH=/usr/local/openblas`, and this will take precedence over any pkg-config file. If there is no pkg-config file (.pc) for OpenBLAS and OPENBLAS_PATH is empty, then headers are assumed to be in /usr/include/openblas and library as assumed to be called 'openblas64' (or 'openblas' if `WHISPER_OPENBLAS_INTERFACE64=0`). If …d5d466c
-
sync : ggml (#2001)
Unverified signature* sync : update scripts * sync : ggml * talk-llama : sync llama.cpp * make : WHISPER_CUBLAS -> WHISPER_CUDA * ci : try to fix sycl build * talk-llama : fix make buildcbbfa9e
-
cmake : copy ggml-common.h to bin
Unverified signaturef592e46
-
cmake : add library versioning (#1352)
kennethge +1: ggerganov Unverified signatureCo-authored-by: Georgi Gerganov <ggerganov@gmail.com>3ab7ee7
-
whisper : add SYCL support (#1863)
Abhilash MajumderUnverified signature* add changes from llama upstream * add sycl abstraction * add sycl build * update cmake * add sycl build config * fix bug * fix bug * refactor build * fix bug * update build * call build * use sycl header * add examples * add target * fix typecast in quant.c * readd fp16 and readme * fix quant typecast * add sample * add readme * remove cxx file check9a168fc
-
build : update CBLAS flags + fix unused var warning (#0)
Unverified signature496c0f1
-
metal : option to embed MSL source into compiled binary (#1842)
Didzis GoskoUnverified signature* ggml : embed Metal library source (ggml-metal.metal) into binary enable by setting WHISPER_EMBED_METAL_LIBRARY * rename the build option * rename the preprocessor directive * generate Metal library embedding assembly on-fly during build processa46b62a
-
cmake : make libwhisper.so position independent (#1792)
trixirtUnverified signatureThis is similar to how libllama.so is built. Signed-off-by: Tom Rix <trix@redhat.com>1cf1553 -
cmake : temporary remove VLA check (#1795)
Unverified signature1a32e6f
-
release : v1.5.4
Unverified signature96799a3
-
release : v1.5.3
Unverified signature1f8a047
-
examples : fix WASM Stack Overflow (#1713)
Unverified signatureFix for problem: """ RuntimeError: Aborted(Stack overflow! Stack cookie has been overwritten at 0x12be2b10, expected hex dwords 0x89BACDFE and 0x2135467, but received 0x00000000 0x00000000) """ That appears when executing the WASM example with the newer versions.57c0e54
-
sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)
Unverified signature* scripts : add sync-ggml-am.sh * sync : ggml (VMM, ARM dot prod fix, etc.) * build : fix CUDA build * ggml : fix some mul mat cases + add tests for src1 F16 https://github.com/ggerganov/ggml/commit/dbd02958fa4f46898f68ca29c27ddcdc58a06f98919a447
-
cmake : set default CUDA architectures (#1667)
bobqianicUnverified signature0969db5
-
release : v1.5.2
Unverified signature9dd774b
-
cmake : install required ggml.h header (#1568)
Gregor JasnyUnverified signature9001318
-
release : v1.5.1
Unverified signature4515273
-
release : v1.5.0
Unverified signature65d366a
-
release : v1.4.3
Unverified signature4d80650
-
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
Unverified signature* sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) * metal : allow env metal variable to override resource path (#1415) * Allow env variable to override resource path * Update ggml-metal.m --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * sync : restore common / main from `master` * sync : restore whisper from `master` * talk-llama : update to latest llama.cpp * ruby : fix build * ggml : fix 32-bit ARM build * ggml : fix MIN / MAX macro collisions + update ios bindings * ggml : fix ifdefs and MIN / MAX again * exampels : fix Obj-C and Swift examples * ggml : fix 32-bit ARM compatibility * ggml : one more attempt to fix 32-bit ARM compat * whisper : fix support for larger graphs --------- Co-authored-by: Chris Raethke <codesoda@users.noreply.github.com>7006035