* 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>
* Clarify doc about where to compile from
* Update examples/stream/README.md
* Update examples/stream/README.md
* Update README.md
---------
Co-authored-by: AI @ Home <>
Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>
* Allocate class on the stack instead of on the heap
* Add class wav_writer
* fix some minor issues
* fix some minor issues
* remove potential misleading API
* Create bench.py
* Various benchmark results
* Update benchmark script with hardware name, and file checks
* Remove old benchmark results
* Add git shorthash
* Round to 2 digits on calculated floats
* Fix the header reference when sorting results
* FIx order of models
* Parse file name
* Simplify filecheck
* Improve print run print statement
* Use simplified model name
* Update benchmark_results.csv
* Process single or lists of processors and threads
* Ignore benchmark results, dont check in
* Move bench.py to extra folder
* Readme section on how to use
* Move command to correct location
* Use separate list for models that exist
* Handle subprocess error in git short hash check
* Fix filtered models list initialization
* metal : init
* whisper : factor out graph builds
* whisper : allocate encoder and decoder using ggml-alloc
* whisper : ggml-alloc is now supported
* whisper : CoreML support ggml-alloc
* build : fix ggml-alloc
* ios : update submodule
* extra : update sync-ggml.sh script to also sync ggml-alloc
* ci : see if this is causing the crash
* whisper : refactor ggml-alloc init
* whisper.android : try to fix build
* whisper : initial Metal version
* ci : try to debug vmem issue
* metal : decoder works on GPU!
* metal : add multi-decoder support
* ggml : fix ggml_nbytes (probably temp solution)
* metal : run "cross" step on the GPU
* whisper : remove ggml_repeat in the encoder
* whisper : offload the Encoder to Metal
* ggml : use simpler ggml_bytes() implementation
* ggml-alloc : try to make CI happy by reducing vram to 128GB
* whisper : add whisper_allocr to wrap ggml_allocr
* whisper : factor out alloc init in a function
* cmake : update to support Metal build
* whisper : add <functional> header
* objc : fix build (no Metal yet)
* ios : add Metal support
* swiftui : fix build
* metal : speed-up KQ multiplication
* metal : sync latest llama.cpp kernels
* readme : add Metal info
* ios : update submodule
* coreml : add code to toggle Core ML config (CPU, ANE, GPU)
* bench : fix timings by running a pre-heat
* bench : start benching the decoder
* whisper : add ggml_mul_mat_pad
* bench : fix uninitialized vars
* whisper : add comment for disabling mul-mat padding
* whisper : add description of ggml_mul_mat_pad
* whisper : clean-up ggml_mul_mat_pad
* metal : remove the "concurrent" flag
* bench : variable n_past
* ios : update SPM package
* --stacktrace signMavenJavaPublication
* added temporary step "Debug gradle signing"
* cd bindings/java
* use GPG_PRIVATE_KEY and GPG_PASSPHRASE
* use secrets.GPG_PRIVATE_KEY and GPG_PASSPHRASE
* Do not use _GNU_SOURCE gratuitously.
What is needed to build whisper.cpp and examples is availability of
stuff defined in The Open Group Base Specifications Issue 6
(https://pubs.opengroup.org/onlinepubs/009695399/) known also as
Single Unix Specification v3 (SUSv3) or POSIX.1-2001 + XSI extensions,
plus some stuff from BSD that is not specified in POSIX.1.
Well, that was true until NUMA support was added recently in ggml,
so enable GNU libc extensions for Linux builds to cover that.
There is no need to penalize musl libc which simply follows standards.
Not having feature test macros in source code gives greater flexibility
to those wanting to reuse it in 3rd party app, as they can build it with
minimal FTM (_XOPEN_SOURCE=600) or other FTM depending on their needs.
It builds without issues in Alpine (musl libc), Ubuntu (glibc), MSYS2.
* examples : include SDL headers before other headers
Avoid macOS build error when _DARWIN_C_SOURCE is not defined, brought by
SDL2 relying on Darwin extension memset_pattern4/8/16 (from string.h).
* make : enable BSD extensions for DragonFlyBSD to expose RLIMIT_MEMLOCK
* make : use BSD-specific FTMs to enable alloca on BSDs
* make : fix OpenBSD build by exposing newer POSIX definitions
* cmake : follow recent FTM improvements from Makefile
* ggml : use sysconf(_SC_PAGESIZE) instead of getpagesize() derived from BSD
sed -i 's,getpagesize(),sysconf(_SC_PAGESIZE),g' ggml.c
* metal : use sysconf(_SC_PAGESIZE) instead of getpagesize() derived from BSD
sed -i 's,getpagesize(),sysconf(_SC_PAGESIZE),g' ggml-metal.m
* make : simplify and correct x86 ISA extensions detection on the host
It got broken in commit c5f9acf4b7 for Haiku and Mac OS (Intel),
which report CPU features in upper case.
Now we're finding the names in case-insensitive manner and as words.
SSE3 detection has been corrected for Linux, which uses PNI for that
(Prescott New Instructions).
* make : use dmesg.boot in FreeBSD/DragonFlyBSD to detect x86 ISA extensions on the host
* make : enable x86 ISA extensions on the host both in CFLAGS and CXXFLAGS
* make : correct AVX x86 ISA extension detection on macOS (Intel) host
It got broken in commit c5f9acf4b7. macOS calls it AVX1.0.
