]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/log
pkg/ggml/sources/llama.cpp
21 months agoEnable build with CUDA 11.0 (make) (#3132)
Vlad [Sat, 16 Sep 2023 14:55:43 +0000 (17:55 +0300)]
Enable build with CUDA 11.0 (make) (#3132)

* CUDA 11.0 fixes

* Cleaner CUDA/host flags separation

Also renamed GGML_ASSUME into GGML_CUDA_ASSUME

21 months agoFixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170)
goerch [Sat, 16 Sep 2023 11:41:33 +0000 (13:41 +0200)]
Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170)

* Fix für #2721

* Reenable tokenizer test for LLaMa

* Add `console.cpp` dependency

* Fix dependency to `common`

* Fixing wrong fix.

* Make console usage platform specific

Work on compiler warnings.

* Adapting makefile

* Remove trailing whitespace

* Adapting the other parts of the makefile

* Fix typo.

* Fixing the last deviations from sentencepiece indicated by test-tokenizer-1

* Simplify logic

* Add missing change...

* Fix ugly compiler warning

* llama_tokenize should accept strings containing NUL now

* Adding huichen's test case

21 months agoexamples : add compiler version and target to build info (#2998)
Cebtenzzre [Fri, 15 Sep 2023 20:59:49 +0000 (16:59 -0400)]
examples : add compiler version and target to build info (#2998)

21 months agocheck C++ code with -Wmissing-declarations (#3184)
Cebtenzzre [Fri, 15 Sep 2023 19:38:27 +0000 (15:38 -0400)]
check C++ code with -Wmissing-declarations (#3184)

21 months agofix build numbers by setting fetch-depth=0 (#3197)
Cebtenzzre [Fri, 15 Sep 2023 19:18:15 +0000 (15:18 -0400)]
fix build numbers by setting fetch-depth=0 (#3197)

21 months agollama : add support for StarCoder model architectures (#3187)
Meng Zhang [Fri, 15 Sep 2023 19:02:13 +0000 (03:02 +0800)]
llama : add support for StarCoder model architectures (#3187)

* add placeholder of starcoder in gguf / llama.cpp

* support convert starcoder weights to gguf

* convert MQA to MHA

* fix ffn_down name

* add LLM_ARCH_STARCODER to llama.cpp

* set head_count_kv = 1

* load starcoder weight

* add max_position_embeddings

* set n_positions to max_positioin_embeddings

* properly load all starcoder params

* fix head count kv

* fix comments

* fix vram calculation for starcoder

* store mqa directly

* add input embeddings handling

* add TBD

* working in cpu, metal buggy

* cleanup useless code

* metal : fix out-of-bounds access in soft_max kernels

* llama : make starcoder graph build more consistent with others

* refactor: cleanup comments a bit

* add other starcoder models: 3B, 7B, 15B

* support-mqa-directly

* fix: remove max_position_embeddings, use n_train_ctx

* Update llama.cpp

Co-authored-by: Georgi Gerganov <redacted>
* Update llama.cpp

Co-authored-by: Georgi Gerganov <redacted>
* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <redacted>
* fix: switch to space from tab

---------

Co-authored-by: Georgi Gerganov <redacted>
21 months agocommon : do not use GNU zero-length __VA_ARGS__ extension (#3195)
Cebtenzzre [Fri, 15 Sep 2023 18:02:01 +0000 (14:02 -0400)]
common : do not use GNU zero-length __VA_ARGS__ extension (#3195)

21 months agometal : fix bug in soft_max kernels (out-of-bounds access) (#3194)
Georgi Gerganov [Fri, 15 Sep 2023 17:17:24 +0000 (20:17 +0300)]
metal : fix bug in soft_max kernels (out-of-bounds access) (#3194)

21 months agoconvert : make ftype optional in simple scripts (#3185)
Cebtenzzre [Fri, 15 Sep 2023 16:29:02 +0000 (12:29 -0400)]
convert : make ftype optional in simple scripts (#3185)

21 months agosync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)
Georgi Gerganov [Fri, 15 Sep 2023 16:06:03 +0000 (19:06 +0300)]
sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)

* sync : ggml (Metal F32 support + reduce ggml-alloc size)

ggml-ci

* llama-bench : fix ggml_cpu_has_metal() duplicate function

ggml-ci

21 months agocmake : fix building shared libs for clang (rocm) on windows (#3176)
Engininja2 [Fri, 15 Sep 2023 12:24:30 +0000 (06:24 -0600)]
cmake : fix building shared libs for clang (rocm) on windows (#3176)

21 months agoflake : use pkg-config instead of pkgconfig (#3188)
Evgeny Kurnevsky [Fri, 15 Sep 2023 08:10:22 +0000 (10:10 +0200)]
flake : use pkg-config instead of pkgconfig (#3188)

pkgconfig is an alias, it got removed from nixpkgs:
https://github.com/NixOS/nixpkgs/blob/295a5e1e2bacd6e246db8b2bb35d2a9415883224/pkgs/top-level/aliases.nix#L1408

21 months agometal : relax conditions on fast matrix multiplication kernel (#3168)
Georgi Gerganov [Fri, 15 Sep 2023 08:09:24 +0000 (11:09 +0300)]
metal : relax conditions on fast matrix multiplication kernel (#3168)

* metal : relax conditions on fast matrix multiplication kernel

* metal : revert the concurrnecy change because it was wrong

* llama : remove experimental stuff

21 months agocmake : fix llama.h location when built outside of root directory (#3179)
Andrei [Fri, 15 Sep 2023 08:07:40 +0000 (04:07 -0400)]
cmake : fix llama.h location when built outside of root directory (#3179)

21 months agoci : Cloud-V for RISC-V builds (#3160)
Ali Tariq [Fri, 15 Sep 2023 08:06:56 +0000 (13:06 +0500)]
ci : Cloud-V for RISC-V builds (#3160)

* Added Cloud-V File

* Replaced Makefile with original one

---------

Co-authored-by: moiz.hussain <redacted>
21 months agollama : remove mtest (#3177)
Roland [Fri, 15 Sep 2023 07:28:45 +0000 (03:28 -0400)]
llama : remove mtest (#3177)

* Remove mtest

* remove from common/common.h and examples/main/main.cpp

21 months agollama : make quantize example up to 2.7x faster (#3115)
Cebtenzzre [Fri, 15 Sep 2023 01:09:53 +0000 (21:09 -0400)]
llama : make quantize example up to 2.7x faster (#3115)

21 months agoflake : allow $out/include to already exist (#3175)
jneem [Thu, 14 Sep 2023 18:54:47 +0000 (13:54 -0500)]
flake : allow $out/include to already exist (#3175)

21 months agocmake : compile ggml-rocm with -fpic when building shared library (#3158)
Andrei [Thu, 14 Sep 2023 17:38:16 +0000 (13:38 -0400)]
cmake : compile ggml-rocm with -fpic when building shared library (#3158)

21 months agoflake : include llama.h in nix output (#3159)
Asbjørn Olling [Thu, 14 Sep 2023 17:25:00 +0000 (19:25 +0200)]
flake : include llama.h in nix output (#3159)

21 months agomake : fix clang++ detection, move some definitions to CPPFLAGS (#3155)
Cebtenzzre [Thu, 14 Sep 2023 17:22:47 +0000 (13:22 -0400)]
make : fix clang++ detection, move some definitions to CPPFLAGS (#3155)

* make : fix clang++ detection

* make : fix compiler definitions outside of CPPFLAGS

21 months agoCI: add FreeBSD & simplify CUDA windows (#3053)
Alon [Thu, 14 Sep 2023 17:21:25 +0000 (20:21 +0300)]
CI: add FreeBSD & simplify CUDA windows (#3053)

* add freebsd to ci

* bump actions/checkout to v3
* bump cuda 12.1.0 -> 12.2.0
* bump Jimver/cuda-toolkit version

* unify and simplify "Copy and pack Cuda runtime"
* install only necessary cuda sub packages

21 months agofalcon : use stated vocab size (#2914)
akawrykow [Thu, 14 Sep 2023 17:19:42 +0000 (10:19 -0700)]
falcon : use stated vocab size (#2914)

21 months agocmake : add relocatable Llama package (#2960)
bandoti [Thu, 14 Sep 2023 17:04:40 +0000 (14:04 -0300)]
cmake : add relocatable Llama package (#2960)

* Keep static libs and headers with install

* Add logic to generate Config package

* Use proper build info

* Add llama as import library

* Prefix target with package name

* Add example project using CMake package

* Update README

* Update README

* Remove trailing whitespace

21 months agodocker : add gpu image CI builds (#3103)
dylan [Thu, 14 Sep 2023 16:47:00 +0000 (09:47 -0700)]
docker : add gpu image CI builds (#3103)

Enables the GPU enabled container images to be built and pushed
alongside the CPU containers.

Co-authored-by: canardleteer <redacted>
21 months agogguf-py : support identity operation in TensorNameMap (#3095)
Kerfuffle [Thu, 14 Sep 2023 16:32:26 +0000 (10:32 -0600)]
gguf-py : support identity operation in TensorNameMap (#3095)

Make try_suffixes keyword param optional.

21 months agofeature : support Baichuan serial models (#3009)
jameswu2014 [Thu, 14 Sep 2023 16:32:10 +0000 (00:32 +0800)]
feature : support Baichuan serial models (#3009)

21 months agospeculative : add heuristic algorithm (#3006)
Leng Yue [Thu, 14 Sep 2023 16:14:44 +0000 (09:14 -0700)]
speculative : add heuristic algorithm (#3006)

* Add heuristic algo for speculative

* Constrain minimum n_draft to 2

* speculative : improve heuristic impl

* speculative : be more rewarding upon guessing max drafted tokens

* speculative : fix typos

---------

Co-authored-by: Georgi Gerganov <redacted>
21 months agowhisper : tokenizer fix + re-enable tokenizer test for LLaMa (#3096)
goerch [Wed, 13 Sep 2023 13:19:44 +0000 (15:19 +0200)]
whisper : tokenizer fix + re-enable tokenizer test for LLaMa (#3096)

* Fix für #2721

* Reenable tokenizer test for LLaMa

* Add `console.cpp` dependency

* Fix dependency to `common`

* Fixing wrong fix.

* Make console usage platform specific

Work on compiler warnings.

* Adapting makefile

* Remove trailing whitespace

* Adapting the other parts of the makefile

* Fix typo.

21 months agocmake : add a compiler flag check for FP16 format (#3086)
Tristan Ross [Wed, 13 Sep 2023 13:08:52 +0000 (06:08 -0700)]
cmake : add a compiler flag check for FP16 format (#3086)

21 months agoCUDA: mul_mat_q RDNA2 tunings (#2910)
Johannes Gäßler [Wed, 13 Sep 2023 09:20:24 +0000 (11:20 +0200)]
CUDA: mul_mat_q RDNA2 tunings (#2910)

* CUDA: mul_mat_q RDNA2 tunings

* Update ggml-cuda.cu

Co-authored-by: Henri Vasserman <redacted>
---------

Co-authored-by: Henri Vasserman <redacted>
21 months agospeculative: add --n-gpu-layers-draft option (#3063)
FK [Wed, 13 Sep 2023 06:50:46 +0000 (08:50 +0200)]
speculative: add --n-gpu-layers-draft option (#3063)

21 months agoarm64 support for windows (#3007)
Eric Sommerlade [Wed, 13 Sep 2023 01:54:20 +0000 (02:54 +0100)]
arm64 support for windows (#3007)

Co-authored-by: Cebtenzzre <redacted>
21 months agoCUDA: fix LoRAs (#3130)
Johannes Gäßler [Tue, 12 Sep 2023 22:15:33 +0000 (00:15 +0200)]
CUDA: fix LoRAs (#3130)

21 months agoCUDA: fix mul_mat_q not used for output tensor (#3127)
Johannes Gäßler [Mon, 11 Sep 2023 20:58:41 +0000 (22:58 +0200)]
CUDA: fix mul_mat_q not used for output tensor (#3127)

21 months agoCUDA: lower GPU latency + fix Windows performance (#3110)
Johannes Gäßler [Mon, 11 Sep 2023 17:55:51 +0000 (19:55 +0200)]
CUDA: lower GPU latency + fix Windows performance (#3110)

21 months agocmake : support build for iOS/tvOS (#3116)
Jhen-Jie Hong [Mon, 11 Sep 2023 11:49:06 +0000 (19:49 +0800)]
cmake : support build for iOS/tvOS (#3116)

* cmake : support build for iOS/tvOS

* ci : add iOS/tvOS build into macOS-latest-cmake

* ci : split ios/tvos jobs

21 months agoCUDA: add device number to error messages (#3112)
Johannes Gäßler [Mon, 11 Sep 2023 11:00:24 +0000 (13:00 +0200)]
CUDA: add device number to error messages (#3112)

21 months agometal : PP speedup (#3084)
Kawrakow [Mon, 11 Sep 2023 07:30:11 +0000 (09:30 +0200)]
metal : PP speedup (#3084)

* Minor speed gains for all quantization types

* metal: faster kernel_scale via float4

* Various other speedups for "small" kernels

* metal: faster soft_max vial float4

* metal: faster diagonal infinity

Although, to me it looks like one should simply
fuse scale + diagnonal infinity + soft_max on the
KQtensor.

* Another faster f16 x f32 matrix multiply kernel

* Reverting the diag infinity change

It does work for PP, but somehow it fails for TG.
Need to look more into it.

* metal: add back faster diagonal infinity

This time more carefully

* metal : minor (readibility)

---------

Co-authored-by: Iwan Kawrakow <redacted>
Co-authored-by: Georgi Gerganov <redacted>
21 months agoconvert: remove most of the n_mult usage in convert.py (#3098)
Erik Scholz [Sun, 10 Sep 2023 15:06:53 +0000 (17:06 +0200)]
convert: remove most of the n_mult usage in convert.py (#3098)

21 months agometal : support for Swift (#3078)
kchro3 [Sat, 9 Sep 2023 09:12:10 +0000 (02:12 -0700)]
metal : support for Swift (#3078)

* Metal support for Swift

* update

* add a toggle for arm/arm64

* set minimum versions for all platforms

* update to use newLibraryWithURL

* bump version

Co-authored-by: Jhen-Jie Hong <redacted>
---------

Co-authored-by: Jhen-Jie Hong <redacted>
21 months agometal : support build for iOS/tvOS (#3089)
Jhen-Jie Hong [Sat, 9 Sep 2023 08:46:04 +0000 (16:46 +0800)]
metal : support build for iOS/tvOS (#3089)

21 months agoflake : add train-text-from-scratch to flake.nix (#3042)
takov751 [Fri, 8 Sep 2023 16:06:26 +0000 (17:06 +0100)]
flake : add train-text-from-scratch to flake.nix (#3042)

21 months agoreadme : fix typo (#3043)
Ikko Eltociear Ashimine [Fri, 8 Sep 2023 16:04:32 +0000 (01:04 +0900)]
readme : fix typo (#3043)

* readme : fix typo

acceleation -> acceleration

* Update README.md

---------

Co-authored-by: Georgi Gerganov <redacted>
21 months agometal : Q3_K speedup (#2995)
Kawrakow [Fri, 8 Sep 2023 16:01:04 +0000 (18:01 +0200)]
metal : Q3_K speedup (#2995)

* Slightly faster Q3_K and Q5_K on metal

* Another Q3_K speedup on metal

Combined with previous commit, we are now +9.6% for TG.
PP is not affected as this happens via the matrix multiplication
templates.

* Slowly progressing on Q3_K on metal

We are now 13% faster than master

* nother small improvement for Q3_K on metal

---------

Co-authored-by: Iwan Kawrakow <redacted>
21 months agoexamples : make n_ctx warning work again (#3066)
Cebtenzzre [Fri, 8 Sep 2023 15:43:35 +0000 (11:43 -0400)]
examples : make n_ctx warning work again (#3066)

This was broken by commit e36ecdcc ("build : on Mac OS enable Metal by
default (#2901)").

21 months agoreadme : update hot tpoics
Georgi Gerganov [Fri, 8 Sep 2023 15:18:04 +0000 (18:18 +0300)]
readme : update hot tpoics

21 months agosync : ggml (CUDA GLM RoPE + POSIX) (#3082)
Georgi Gerganov [Fri, 8 Sep 2023 14:58:07 +0000 (17:58 +0300)]
sync : ggml (CUDA GLM RoPE + POSIX) (#3082)

ggml-ci

21 months agobuild : do not use _GNU_SOURCE gratuitously (#2035)
Przemysław Pawełczyk [Fri, 8 Sep 2023 12:09:21 +0000 (14:09 +0200)]
build : do not use _GNU_SOURCE gratuitously (#2035)

* Do not use _GNU_SOURCE gratuitously.

What is needed to build llama.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,
so enable GNU libc extensions for Linux builds to cover that.

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
FTMs set by Makefile here or other FTMs depending on their needs.

It builds without issues in Alpine (musl libc), Ubuntu (glibc), MSYS2.

* make : enable Darwin extensions for macOS to expose RLIMIT_MEMLOCK

* 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

21 months agodocker : add git to full-cuda.Dockerfile main-cuda.Dockerfile (#3044)
hongbo.mo [Fri, 8 Sep 2023 10:57:55 +0000 (18:57 +0800)]
docker : add git to full-cuda.Dockerfile main-cuda.Dockerfile (#3044)

21 months agoUpdate deprecated GGML TheBloke links to GGUF (#3079)
Yui [Fri, 8 Sep 2023 10:32:55 +0000 (12:32 +0200)]
Update deprecated GGML TheBloke links to GGUF (#3079)

21 months agoggml-alloc : correctly check mmap return value for errors (#3075)
slaren [Fri, 8 Sep 2023 02:04:56 +0000 (04:04 +0200)]
ggml-alloc : correctly check mmap return value for errors (#3075)

21 months agoenable CPU HBM (#2603)
Kunshang Ji [Fri, 8 Sep 2023 01:46:56 +0000 (09:46 +0800)]
enable CPU HBM (#2603)

* add cpu hbm support

* add memalign 0 byte check

* Update ggml.c

* Update llama.cpp

* ggml : allow ggml_init with 0 size

* retrigger ci

* fix code style

---------

Co-authored-by: Georgi Gerganov <redacted>
21 months agoconvert : fix F32 ftype not being saved (#3048)
Cebtenzzre [Thu, 7 Sep 2023 18:27:42 +0000 (14:27 -0400)]
convert : fix F32 ftype not being saved (#3048)

21 months agofix some warnings from gcc and clang-tidy (#3038)
Cebtenzzre [Thu, 7 Sep 2023 17:22:29 +0000 (13:22 -0400)]
fix some warnings from gcc and clang-tidy (#3038)

Co-authored-by: xaedes <redacted>
21 months agomake : improve test target (#3031)
Cebtenzzre [Thu, 7 Sep 2023 14:15:01 +0000 (10:15 -0400)]
make : improve test target (#3031)

21 months agomake : fix CPPFLAGS (#3035)
Cebtenzzre [Thu, 7 Sep 2023 14:13:50 +0000 (10:13 -0400)]
make : fix CPPFLAGS (#3035)

21 months agollama-bench : use two tokens in the warmup run for prompt evals (#3059)
slaren [Thu, 7 Sep 2023 13:52:34 +0000 (15:52 +0200)]
llama-bench : use two tokens in the warmup run for prompt evals (#3059)

21 months agometal : parallel RoPE on Metal (#3024)
Kawrakow [Thu, 7 Sep 2023 13:45:01 +0000 (15:45 +0200)]
metal : parallel RoPE on Metal (#3024)

* Parallel RoPE on metal

* PR suggestion

---------

Co-authored-by: Iwan Kawrakow <redacted>
21 months agometal : correct fix of kernel_norm (#3060)
Kawrakow [Thu, 7 Sep 2023 13:42:42 +0000 (15:42 +0200)]
metal : correct fix of kernel_norm (#3060)

Co-authored-by: Iwan Kawrakow <redacted>
Co-authored-by: Georgi Gerganov <redacted>
21 months agometal : fix kernel_norm (fixes Falcon on Metal) (#3057)
Georgi Gerganov [Thu, 7 Sep 2023 12:49:09 +0000 (15:49 +0300)]
metal : fix kernel_norm (fixes Falcon on Metal) (#3057)

* metal : fix kernel_norm

ggml-ci

* metal : put warning in kernel_norm to not combine the loops

* metal : restore original F16 mat-vec multiplication

It works after the norm fixes

* common : don't do warm-up with more than n_batch tokens (close #3058)

ggml-ci

* metal : minor

21 months agoggml : posixify madvise and pagesize (#3037)
Przemysław Pawełczyk [Thu, 7 Sep 2023 08:15:06 +0000 (10:15 +0200)]
ggml : posixify madvise and pagesize (#3037)

* llama : use posix_madvise() instead of madvise() derived from BSD

sed -i 's,\<madvise\>,posix_&,g;s,\<MADV_,POSIX_&,g' llama.cpp

* 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

21 months agok-quants : fix zero-weight guard in Q6_K (ref #3040)
Georgi Gerganov [Wed, 6 Sep 2023 09:40:57 +0000 (12:40 +0300)]
k-quants : fix zero-weight guard in Q6_K (ref #3040)

21 months agoconvert-llama-ggml-to-gguf: Try to handle files older than GGJTv3 (#3023)
Kerfuffle [Wed, 6 Sep 2023 08:49:11 +0000 (02:49 -0600)]
convert-llama-ggml-to-gguf: Try to handle files older than GGJTv3 (#3023)

* convert-llama-ggmlv3-to-gguf: Try to handle files older than GGJTv3

* Better error messages for files that cannot be converted

* Add file type to GGUF output

* Rename to convert-llama-ggml-to-gguf.py

* Include original file type information in description

* Improve some informational output

21 months agobuild : add LLAMA_METAL_NDEBUG flag (#3033)
Cebtenzzre [Tue, 5 Sep 2023 22:21:10 +0000 (18:21 -0400)]
build : add LLAMA_METAL_NDEBUG flag (#3033)

21 months agomake : use new flag variables for recent changes (#3019)
Cebtenzzre [Tue, 5 Sep 2023 19:12:00 +0000 (15:12 -0400)]
make : use new flag variables for recent changes (#3019)

21 months agoexamples : replace fprintf to stdout with printf (#3017)
Cebtenzzre [Tue, 5 Sep 2023 19:10:27 +0000 (15:10 -0400)]
examples : replace fprintf to stdout with printf (#3017)

21 months agoconvert: fix convert.py not working with int filename_stem (#3028)
Erik Scholz [Tue, 5 Sep 2023 17:41:00 +0000 (19:41 +0200)]
convert: fix convert.py not working with int filename_stem (#3028)

* fix implicit int to string conversion
* convert : remove an obsolete pyright comment

---------

Co-authored-by: Cebtenzzre <redacted>
21 months agoGuard against all weights in a super-block being zero (#3010)
Kawrakow [Tue, 5 Sep 2023 07:55:33 +0000 (09:55 +0200)]
Guard against all weights in a super-block being zero (#3010)

* Guard against all weights in a super-block being zero

* Also guard against extremely small weights

Closes #2982

---------

Co-authored-by: Iwan Kawrakow <redacted>
21 months agollama : update logic for number of threads when using BLAS
Georgi Gerganov [Tue, 5 Sep 2023 07:46:39 +0000 (10:46 +0300)]
llama : update logic for number of threads when using BLAS

21 months agospeculative : add grammar support (#2991)
Georgi Gerganov [Tue, 5 Sep 2023 05:46:17 +0000 (08:46 +0300)]
speculative : add grammar support (#2991)

* speculative : add grammar support

* grammars : add json_arr.gbnf

* grammar : add comments to new grammar file

* grammar : remove one nested level

* common : warm-up with 2 tokens - seems to work better

* speculative : print draft token pieces

* speculative : reuse grammar parser + better logs and comments

* speculative : avoid grammar_mem

* make : fix speculative build

21 months agopy : minor
Georgi Gerganov [Mon, 4 Sep 2023 19:50:50 +0000 (22:50 +0300)]
py : minor

21 months agobuild : on Mac OS enable Metal by default (#2901)
Georgi Gerganov [Mon, 4 Sep 2023 19:26:24 +0000 (22:26 +0300)]
build : on Mac OS enable Metal by default (#2901)

* build : on Mac OS enable Metal by default

* make : try to fix build on Linux

* make : move targets back to the top

* make : fix target clean

* llama : enable GPU inference by default with Metal

* llama : fix vocab_only logic when GPU is enabled

* common : better `n_gpu_layers` assignment

* readme : update Metal instructions

* make : fix merge conflict remnants

* gitignore : metal

21 months agoggml-opencl : store GPU buffer in ggml_tensor::extra (#2994)
slaren [Mon, 4 Sep 2023 12:59:52 +0000 (14:59 +0200)]
ggml-opencl : store GPU buffer in ggml_tensor::extra (#2994)

21 months agollama-bench : make cpp file non-executable (#2999)
Cebtenzzre [Mon, 4 Sep 2023 10:40:18 +0000 (06:40 -0400)]
llama-bench : make cpp file non-executable (#2999)

21 months agomake : add speculative example (#3003)
Leng Yue [Mon, 4 Sep 2023 10:39:57 +0000 (03:39 -0700)]
make : add speculative example (#3003)

21 months agoserver : add a subtle loading animation to the edit box (#2466)
Aarni Koskela [Mon, 4 Sep 2023 08:28:55 +0000 (10:28 +0200)]
server : add a subtle loading animation to the edit box (#2466)

* editorconfig: add override for the server HTML (which already is 2-space indented)

* server: add a subtle loading animation to the edit box

21 months ago2x faster (rms) norm cuda kernels (3.7% e2e improvement) (#2985)
Jiahao Li [Mon, 4 Sep 2023 06:53:30 +0000 (14:53 +0800)]
2x faster (rms) norm cuda kernels (3.7% e2e improvement) (#2985)

* 2x faster (rms) norm cuda kernels

* Fix code style

21 months agoggml-alloc : use virtual memory for measurement (#2973)
slaren [Sun, 3 Sep 2023 18:34:09 +0000 (20:34 +0200)]
ggml-alloc : use virtual memory for measurement (#2973)

* ggml-alloc : use virtual memory for measurement

* compatibility fixes for MAP_ANONYMOUS

* fallback to fixed address for systems without virtual memory

21 months agospeculative : PoC for speeding-up inference via speculative sampling (#2926)
Georgi Gerganov [Sun, 3 Sep 2023 12:12:08 +0000 (15:12 +0300)]
speculative : PoC for speeding-up inference via speculative sampling (#2926)

* speculative : initial example

* speculative : print encoding speed

* speculative : add --draft CLI arg

21 months agoperplexity : fix ETA by warming up the model with an empty run
Georgi Gerganov [Sun, 3 Sep 2023 10:42:56 +0000 (13:42 +0300)]
perplexity : fix ETA by warming up the model with an empty run

21 months agogguf(python): Fix special vocab handling when id < 0 (#2984)
Kerfuffle [Sun, 3 Sep 2023 10:38:43 +0000 (04:38 -0600)]
gguf(python): Fix special vocab handling when id < 0 (#2984)

21 months agometal : restore 363f0bf and fix reduce in F16_F32 kernels (#2986)
Georgi Gerganov [Sun, 3 Sep 2023 10:23:33 +0000 (13:23 +0300)]
metal : restore 363f0bf and fix reduce in F16_F32 kernels (#2986)

21 months agocov : disable comment in PRs (#2989)
Alon [Sun, 3 Sep 2023 10:19:01 +0000 (13:19 +0300)]
cov : disable comment in PRs (#2989)

21 months agollama : fix bpe tokenize from byte (#2889)
opparco [Sun, 3 Sep 2023 10:18:09 +0000 (19:18 +0900)]
llama : fix bpe tokenize from byte (#2889)

21 months agometal : revert 6af0bab until we fix it
Georgi Gerganov [Sun, 3 Sep 2023 09:40:56 +0000 (12:40 +0300)]
metal : revert 6af0bab until we fix it

This restores the generated text to be the same as before #2959

21 months agocov : add Code Coverage and codecov.io integration (#2928)
Alon [Sun, 3 Sep 2023 08:48:49 +0000 (11:48 +0300)]
cov : add Code Coverage and codecov.io integration (#2928)

* update .gitignore

* makefile: add coverage support (lcov, gcovr)

* add code-coverage workflow

* update code coverage workflow

* wun on ubuntu 20.04

* use gcc-8

* check why the job hang

* add env vars

* add LLAMA_CODE_COVERAGE=1 again

* - add CODECOV_TOKEN
- add missing make lcov-report

* install lcov

* update make file -pb flag

* remove unused  GGML_NITER from workflows

* wrap coverage output files in COV_TARGETS

21 months agoopencl : fix a bug in ggml_cl_pool_malloc() for ggml_cl_mul_mat_f32() (#2955)
Wentai Zhang [Sun, 3 Sep 2023 08:46:44 +0000 (16:46 +0800)]
opencl : fix a bug in ggml_cl_pool_malloc() for ggml_cl_mul_mat_f32() (#2955)

Co-authored-by: Wentai Zhang <redacted>
21 months agometal : more optimizations (#2959)
Kawrakow [Sun, 3 Sep 2023 08:06:22 +0000 (11:06 +0300)]
metal : more optimizations (#2959)

* Very minor speedup via simd-group synchronization in f16 x f32

* Another very minor speedup on metal

* Quite significant PP speedup on metal

* Another attempt

* Minor

* Massive improvement for TG for fp16

* ~4-5% improvement for Q8_0 TG on metal

---------

Co-authored-by: Iwan Kawrakow <redacted>
Co-authored-by: Georgi Gerganov <redacted>
21 months agoswift : add support for k-quants (#2983)
kchro3 [Sun, 3 Sep 2023 06:21:05 +0000 (23:21 -0700)]
swift : add support for k-quants (#2983)

21 months agoconvert.py : BPE fixes (#2938)
Kerfuffle [Sun, 3 Sep 2023 05:52:13 +0000 (23:52 -0600)]
convert.py : BPE fixes (#2938)

* convert.py: BPE fixes?

* Remove unnecessary conditional in addl token error handling

21 months agodocs : add `catai` to `README.md` (#2967)
Ido S [Sun, 3 Sep 2023 05:50:51 +0000 (08:50 +0300)]
docs : add `catai` to `README.md` (#2967)

21 months agoexamples : fix gpt-neox (#2943)
momonga [Sun, 3 Sep 2023 05:36:28 +0000 (14:36 +0900)]
examples : fix gpt-neox (#2943)

Co-authored-by: mmnga <redacted>
21 months agoswift : add missing c file to Package.swift (#2978)
kchro3 [Sun, 3 Sep 2023 05:27:25 +0000 (22:27 -0700)]
swift : add missing c file to Package.swift (#2978)

21 months agomake : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS (#2886)
Cebtenzzre [Sun, 3 Sep 2023 05:26:59 +0000 (01:26 -0400)]
make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS (#2886)

* make : remove unused -DGGML_BIG_ENDIAN

* make : put preprocessor stuff in CPPFLAGS

* make : pass Raspberry Pi arch flags to g++ as well

* make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS

* make : fix inverted conditional

21 months agologging: Fix creating empty file even when disabled (#2966)
Kerfuffle [Sat, 2 Sep 2023 17:53:55 +0000 (11:53 -0600)]
logging: Fix creating empty file even when disabled (#2966)

* logging: Fix creating empty file even when disabled

* Minor formatting fix

Co-authored-by: staviq <redacted>
---------

Co-authored-by: staviq <redacted>
21 months agoreadme : update clblast instructions (#2903)
bandoti [Sat, 2 Sep 2023 12:53:18 +0000 (09:53 -0300)]
readme : update clblast instructions (#2903)

* Update Windows CLBlast instructions

* Update Windows CLBlast instructions

* Remove trailing whitespace

21 months agometal : show all Metal device instances in the system (#2952)
Karsten Weiss [Sat, 2 Sep 2023 12:29:09 +0000 (14:29 +0200)]
metal : show all Metal device instances in the system (#2952)

* ggml_metal_init: Show all Metal device instances in the system

Also show the default Metal device that was picked.

* Update ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <redacted>
21 months agok-quants : fix build on armv7 (android only) (#2920)
Jhen-Jie Hong [Sat, 2 Sep 2023 12:23:45 +0000 (20:23 +0800)]
k-quants : fix build on armv7 (android only) (#2920)

* k-quants : fix build on armv7

* ggml : cleanup unused arm32 specific impl

* k-quants : avoid some unused vzero / mzero define

* ggml-alloc : use 4g for MEASURE_MAX_SIZE in 32-bit arm

21 months agoserver : avoid aniprompt in probabilities of final response (#2849)
Jhen-Jie Hong [Sat, 2 Sep 2023 00:31:46 +0000 (08:31 +0800)]
server : avoid aniprompt in probabilities of final response (#2849)