]>
git.djapps.eu Git - pkg/ggml/sources/ggml/log
Georgi Gerganov [Tue, 18 Jul 2023 11:40:53 +0000 (14:40 +0300)]
ci : update to be able to run locally
Georgi Gerganov [Tue, 18 Jul 2023 08:10:40 +0000 (11:10 +0300)]
ggml : sync llama.cpp (fix PERF + CUDA dup cont support)
Georgi Gerganov [Mon, 17 Jul 2023 14:17:07 +0000 (17:17 +0300)]
ci : disable wget progress
Georgi Gerganov [Mon, 17 Jul 2023 13:35:06 +0000 (16:35 +0300)]
ci : use models-mnt
Georgi Gerganov [Sun, 16 Jul 2023 17:55:06 +0000 (20:55 +0300)]
ci : integrate with ggml-org/ci (#393)
* ci : add initial scripts
* ci : remove setup.sh
* run : add deps
* run : fix
* ci : remove deps
* ci : ignore test-opt
* ci : fix ctest
* ci : induce error in ci-1
* ci : try to capture exit codes
* ci : try fix pipefail
* ci : output time of commands
* ci : disable test-opt for release as well
* ci : generate README.md
* ci : update README.md
* ci : fix header
* ci : utilize gg_printf
row 0
row 1 testing adafa
asdfdsa
* ci : move out the README.md header generation
row 0
row 1 dsfkdjs
adslfkaj ska
test
* ci : fix
row 0
row 1 dsfkdjs
adslfkaj ska
test
* ci : induce error
* ci : fix error
remove assert(false)
* ci : fix ctest summary
* ci : fix comment
minor
test test
* ci : fix gg_printf usage
* ci : switch ci-1 to Release
* ci : try to simplify
* ci : induce error
* Revert "ci : induce error"
This reverts commit
a9cef1eeb174764a0a1eb5b13753a7637b10f9dd .
* ci : induce error
* ci : fix pipefail + status
* ci : try to fix pipefail
* ci : fix output
* ci : fix return codes
* ci : test
* ci : fix test
* ci : add gpt-2 ci
* ci : fix gpt-2 test
* ci : gpt-2 seed
* ci : fix checks
* ci : time gpt-2
* ci : fix gpt-2 output
* ci : try to fix duplicated output
* ci : try fix duplicated output
* ci : cat gpt-2 output
* ci : finally fix double output
* ci : try to add "set -x"
* ci : fix model var
* ci : append logs
* ci : add mpt
* ci : fix model dir creation
* ci : fix mpt convert
* ci : add mpt config.json
* ci : add configuration_mpt.py
* ci : don't run test-opt on low perf systems
* ci : do not run test-opt in Debug
Georgi Gerganov [Sat, 15 Jul 2023 11:31:18 +0000 (14:31 +0300)]
ggml : sync llama.cpp (CUDA add/mul bcast + Metal fix + custom RoPE)
johnson442 [Fri, 14 Jul 2023 17:58:51 +0000 (18:58 +0100)]
starcoder : mmap (and gpu) example (#338)
* Add basic mmap & GPU offload starcoder example
* starcode-mmap : adapt to new ggml API
---------
Co-authored-by: Georgi Gerganov <redacted>
Johannes Gäßler [Fri, 14 Jul 2023 17:55:34 +0000 (19:55 +0200)]
cuda : fix CUDA arch: OFF -> 52;61 (#389)
Georgi Gerganov [Fri, 14 Jul 2023 13:58:10 +0000 (16:58 +0300)]
ggml : sync llama.cpp (fix CUDA build, faster Metal)
close #379
Jiahao Li [Fri, 14 Jul 2023 12:10:59 +0000 (20:10 +0800)]
cuda : support GLM-style RoPE (#383)
Georgi Gerganov [Fri, 14 Jul 2023 12:02:12 +0000 (15:02 +0300)]
ggml : retire custom ggml_2d impl in favor of general (#352)
David Miller [Fri, 14 Jul 2023 11:38:47 +0000 (04:38 -0700)]
ggml : general conv_2d CPU implementation (#352)
* Conv2d s0 == s1 == 1, d0 == d1 == 1, variable padding
* Mark unused varibles
* Support variable strides
* Handle all non-kernel-width convolutions with same general conv2d
* General 2d Conv
* Remove old function
* Group functions
* Rearrange
* General Conv2d implementation
* Clean up whitespace
Georgi Gerganov [Fri, 14 Jul 2023 08:13:55 +0000 (11:13 +0300)]
ggml : fix mul_mat src1 indexing when not contiguous and non-F32 (#386)
Georgi Gerganov [Fri, 14 Jul 2023 08:03:55 +0000 (11:03 +0300)]
ggml : fix mul_mat src1 indexing when src1 is not contiguous (#386)
Georgi Gerganov [Wed, 12 Jul 2023 17:52:37 +0000 (20:52 +0300)]
ggml : apply mul_mat broadcast fix (sync llama.cpp)
Georgi Gerganov [Wed, 12 Jul 2023 17:38:49 +0000 (20:38 +0300)]
cuda : sync llama.cpp
M. Yusuf Sarıgöz [Wed, 12 Jul 2023 17:39:14 +0000 (20:39 +0300)]
ggml : broadcast mul_mat + conv batch support (#325)
* ggml : make src0 broadcast-able into src1 for ggml_mul_mat
* WIP: batch inference support for conv_2d
* Impl batch inference support cov_2d
* Correct offset in Conv2D
---------
Co-authored-by: Georgi Gerganov <redacted>
Georgi Gerganov [Wed, 12 Jul 2023 11:18:20 +0000 (14:18 +0300)]
ggml : pool naming changes + coding style fixes
Jiahao Li [Wed, 12 Jul 2023 10:52:47 +0000 (18:52 +0800)]
ggml : add CUDA gelu op (#374)
Borislav Stanimirov [Wed, 12 Jul 2023 10:43:30 +0000 (13:43 +0300)]
ggml : basic implementation of 1d and 2d pools (#375)
pools and tests
no lenet
Georgi Gerganov [Wed, 12 Jul 2023 08:39:10 +0000 (11:39 +0300)]
ggml : revert CUDA broadcasting changes until fixed
Georgi Gerganov [Tue, 11 Jul 2023 19:19:42 +0000 (22:19 +0300)]
ggml : remove unused function (#328)
Georgi Gerganov [Tue, 11 Jul 2023 19:18:48 +0000 (22:18 +0300)]
ggml : fix compile warnings after #328
Arjun [Tue, 11 Jul 2023 19:11:45 +0000 (00:41 +0530)]
ggml : add callback to abort ggml_graph_compute() (#328)
* mechanism to abort ggml_graph_compute
* use pthread_cancel
* forgot to commit ggml.h
* static always_false()
Co-authored-by: Georgi Gerganov <redacted>
* accept callback data
* proper function prototype
* return exit status
* remove pthread_cancel and join every thread
* put abort_callback onto cplan
* cplan abort_callback in ggml.c
* make sure all threads abort
---------
Co-authored-by: Georgi Gerganov <redacted>
Jiahao Li [Tue, 11 Jul 2023 18:12:57 +0000 (02:12 +0800)]
ggml : use a single kernel for CUDA mul op (#373)
Borislav Stanimirov [Tue, 11 Jul 2023 18:10:40 +0000 (21:10 +0300)]
tests : ifdef for #pragma GCC (#370)
Georgi Gerganov [Tue, 11 Jul 2023 18:10:14 +0000 (21:10 +0300)]
readme : add link to ggllm.cpp repo (close #361)
Jiahao Li [Tue, 11 Jul 2023 18:06:05 +0000 (02:06 +0800)]
ggml : broadcast ggml_add() for F32 (#359)
* Support broadcast add for fp32
* Use single kernel for broadcast add
Jiahao Li [Tue, 11 Jul 2023 17:58:02 +0000 (01:58 +0800)]
ggml : support norm op on CUDA (#364)
Tom Jobbins [Tue, 11 Jul 2023 17:54:36 +0000 (18:54 +0100)]
starcoder : fix for ggml-model.bin being saved in wrong directory + use argparse (#363)
* Fix for starcoder ggml-model.bin being saved in wrong directory. Modernise by using argparse.
* Make sure output directory exists
goerch [Tue, 11 Jul 2023 17:39:54 +0000 (19:39 +0200)]
ggml : fix ggml_set_xxx (#354)
`ggml_set_i32`/`ggml_set_f32` are in line with `ggml_set_i32_1d`/`ggml_set_f32_1d` then.
Daulet Zhanguzin [Tue, 11 Jul 2023 17:26:22 +0000 (10:26 -0700)]
ggml : fix Alibi implementation (#351)
* correct Alibi implementation
* update f16 too
Georgi Gerganov [Tue, 11 Jul 2023 16:36:52 +0000 (19:36 +0300)]
ggml : sync llama.cpp (fix for #341)
Georgi Gerganov [Mon, 10 Jul 2023 19:05:13 +0000 (22:05 +0300)]
ggml : fix docs about element access (close #348)
the-crypt-keeper [Mon, 10 Jul 2023 18:41:58 +0000 (14:41 -0400)]
starcoder : add <|end_of_turn|> token handling in order to support openchat/opencoderplus (#343)
* Add <|end_of_turn|> token handling to support openchat/opencoderplus
* The opencoder EOT occurs inside the prompt, so we should only break if the model actually generated it
---------
Co-authored-by: Mike <redacted>
Sam Spilsbury [Mon, 10 Jul 2023 18:40:29 +0000 (21:40 +0300)]
pkg-config : fix typo in includedir (#367)
Georgi Gerganov [Mon, 10 Jul 2023 18:40:05 +0000 (21:40 +0300)]
ggml : sync llama.cpp (changes to ggml_graph_compute() API) (#368)
Georgi Gerganov [Thu, 6 Jul 2023 16:41:18 +0000 (19:41 +0300)]
ggml : minor indentation
Borislav Stanimirov [Thu, 6 Jul 2023 07:24:39 +0000 (10:24 +0300)]
ggml : restore GGML_RESTRICT (#350)
Georgi Gerganov [Wed, 5 Jul 2023 17:38:55 +0000 (20:38 +0300)]
Georgi Gerganov [Wed, 5 Jul 2023 17:38:20 +0000 (20:38 +0300)]
tests : sync from llama.cpp and disable some obsolete tests
Georgi Gerganov [Wed, 5 Jul 2023 17:14:13 +0000 (20:14 +0300)]
ggml : sync llama.cpp (generalize quantize_fns + CUDA improvements)
Andrei [Tue, 4 Jul 2023 19:53:42 +0000 (15:53 -0400)]
cmake : fix public header path for submodules (#342)
Georgi Gerganov [Tue, 4 Jul 2023 17:27:19 +0000 (20:27 +0300)]
whisper : fix wrong variable name from previous commit
Sam Spilsbury [Tue, 4 Jul 2023 17:35:13 +0000 (20:35 +0300)]
build : add pkg-config file (#335)
This makes it easier for other library consumers to find
the library and link to it.
Fixes #334
Sam Spilsbury [Tue, 4 Jul 2023 17:34:28 +0000 (20:34 +0300)]
cmake : install the header file to ggml/ggml.h (#333)
Fixes #332
Georgi Gerganov [Tue, 4 Jul 2023 17:24:22 +0000 (20:24 +0300)]
whisper : sync whisper.cpp (tinydiarize + OpenVINO)
Sam Spilsbury [Tue, 4 Jul 2023 13:30:21 +0000 (16:30 +0300)]
readme : add link to ggml-gobject (#336)
This enables also some bindings to python (through pygi), gjs, vala, csharp, etc. However `ggml-gobject`s main purpose is to make the library a bit more friendly to the desktop platform, eg, by providing asynchronous operation, a DBus service, etc.
Jakob Frick [Tue, 4 Jul 2023 13:26:57 +0000 (14:26 +0100)]
dolly : update error print behavior (#337)
Borislav Stanimirov [Tue, 4 Jul 2023 13:26:29 +0000 (16:26 +0300)]
dolly : disable interactive_port on Windows (#339)
Jakob Frick [Sun, 2 Jul 2023 18:48:02 +0000 (14:48 -0400)]
dolly : add interactive prompt and port mode (#319)
* update basic function to execute prompt
* try to factor our prediciton loop
* update code
* update prompt things
* only render at the end
* add basic server port
* refactor
* fix client file descriptor
* undo common.h style changes
* undo sytle changes to main.cpp
* fix check for interactive port
Georgi Gerganov [Sun, 2 Jul 2023 18:41:23 +0000 (21:41 +0300)]
examples : remove whitespace
Hirochika Matsumoto [Sun, 2 Jul 2023 16:47:47 +0000 (01:47 +0900)]
examples : use GGML_FILE_MAGIC where possible (#323)
sjinzh [Sun, 2 Jul 2023 16:36:53 +0000 (00:36 +0800)]
zig : add tests codes using zig (#315)
* update build.zig
* zig : add tests by zig
* zig : add tests codes using zig
* zig : add tests codes using zig
Hugo Rosenkranz-Costa [Sun, 2 Jul 2023 16:05:24 +0000 (18:05 +0200)]
mpt : convert model weights part by part to save memory (#314)
* mpt : update conversion script to load model weights part by part
* mpt : add usage README
Borislav Stanimirov [Sun, 2 Jul 2023 15:54:16 +0000 (18:54 +0300)]
ggml : generalize interface for 1d and 2d convolutions (#313)
* conv_1d wip
* conv_1d opt
* conv_1d done
* conv_1 improve alias func name
* conv_2d wip
* conv size to separate func
* conv2d done
---------
Co-authored-by: Georgi Gerganov <redacted>
Georgi Gerganov [Sun, 2 Jul 2023 15:53:42 +0000 (18:53 +0300)]
ggml : disable ggml_rope_back for ChatGLM
Georgi Gerganov [Sun, 2 Jul 2023 15:33:41 +0000 (18:33 +0300)]
ggml : remove tensor ptr from export for now (close #267)
Not used for now
Georgi Gerganov [Sun, 2 Jul 2023 15:26:26 +0000 (18:26 +0300)]
ggml : fix enum order for TANH (#316)
PAB [Sun, 2 Jul 2023 15:25:37 +0000 (17:25 +0200)]
ggml : add `ELU`, `TANH`, `ARGMAX` (#316)
* add: `elu` activation
* add: `tanh` activation
* add: `argmax`
* ggml : rearrange ops - put "tanh" after "step"
---------
Co-authored-by: Georgi Gerganov <redacted>
goerch [Sun, 2 Jul 2023 15:13:23 +0000 (17:13 +0200)]
ggml : add GGML_TENSOR_LOCALS helper macros (#309)
* [WIP] ref #292
* Further code reduction
* ggml : minor style fixes
* ggml : hide op locals in source file
---------
Co-authored-by: Georgi Gerganov <redacted>
the-crypt-keeper [Sun, 2 Jul 2023 14:52:52 +0000 (10:52 -0400)]
starcoder : add repeat penalty (#311)
* implement repeat penalty processing for starcoder
* show effective parameters at starcoder startup
---------
Co-authored-by: Mike Ravkine <redacted>
Georgi Gerganov [Sun, 2 Jul 2023 14:33:57 +0000 (17:33 +0300)]
ggml : sync latest llama.cpp (ggml_task_type changes + GPU backends)
sjinzh [Mon, 26 Jun 2023 20:48:31 +0000 (04:48 +0800)]
zig : add tests by zig (#307)
* update build.zig
* zig : add tests by zig
Jiahao Li [Mon, 26 Jun 2023 20:47:31 +0000 (04:47 +0800)]
ggml : support ChatGLM-style RoPE (#305)
Georgi Gerganov [Mon, 26 Jun 2023 20:26:37 +0000 (23:26 +0300)]
ggml : increase max name size to 48
Georgi Gerganov [Mon, 26 Jun 2023 18:10:24 +0000 (21:10 +0300)]
ggml : sync llama.cpp (NUMA + thread improvements + k-quants)
Playdev [Sun, 25 Jun 2023 13:50:39 +0000 (22:50 +0900)]
py : add requirements.txt (#201)
* Add requirements.txt
* Fix README.md files
M. Yusuf Sarıgöz [Sun, 25 Jun 2023 13:45:34 +0000 (16:45 +0300)]
readme : add link to CLIP example (#298)
Georgi Gerganov [Sun, 25 Jun 2023 13:39:57 +0000 (16:39 +0300)]
ggml : fix invalid src0 dereference
Georgi Gerganov [Sun, 25 Jun 2023 13:38:17 +0000 (16:38 +0300)]
ggml : remove _GNU_SOURCE
ref : https://github.com/ggerganov/whisper.cpp/pull/1027
sjinzh [Sun, 25 Jun 2023 13:36:09 +0000 (21:36 +0800)]
zig : update build.zig (#296)
Georgi Gerganov [Sun, 25 Jun 2023 13:09:34 +0000 (16:09 +0300)]
readme : add roadmap + manifesto
M. Yusuf Sarıgöz [Sun, 25 Jun 2023 12:59:24 +0000 (15:59 +0300)]
ggml : do not round up the conv 2D row size (#274)
Georgi Gerganov [Sun, 25 Jun 2023 12:38:55 +0000 (15:38 +0300)]
whisper : fix ifdef
Georgi Gerganov [Sun, 25 Jun 2023 12:37:02 +0000 (15:37 +0300)]
opencl : remove ggml-opencl.c
Georgi Gerganov [Sun, 25 Jun 2023 12:35:05 +0000 (15:35 +0300)]
whisper : sync latest whisper.cpp
Georgi Gerganov [Sun, 25 Jun 2023 11:31:01 +0000 (14:31 +0300)]
whisper : sync latest whisper.cpp
Georgi Gerganov [Sun, 25 Jun 2023 11:20:41 +0000 (14:20 +0300)]
common : fix trailing whitespace
Georgi Gerganov [Sun, 25 Jun 2023 11:19:47 +0000 (14:19 +0300)]
whisper : sync latest whisper.cpp
Georgi Gerganov [Sun, 25 Jun 2023 10:07:18 +0000 (13:07 +0300)]
readme : add encodec.cpp link
Georgi Gerganov [Sat, 24 Jun 2023 17:58:42 +0000 (20:58 +0300)]
readme : add BioGPT example link
LoganDark [Sat, 24 Jun 2023 17:47:53 +0000 (10:47 -0700)]
ggml : add custom mapping functions (#264)
* Add custom mapping functions
The current mapping functions are basically jokes, add some real
ones. These ones get access to the actual tensor structs so they
can do things like
- Know the dimensions they are operating on
- Work with tensors with more than 2 dimensions, or transposed
- Operate on two differently sized tensors (like matmul)
- Use their own thread pool that does a better job than ggml does.
Among other things ...
* fix ordering mistake
* ggml : custom operators support scratch buffers
---------
Co-authored-by: Georgi Gerganov <redacted>
sjinzh [Sat, 24 Jun 2023 17:03:13 +0000 (01:03 +0800)]
zig : add zig build system support (#279)
* add zig build system support
* add zig build system support
Georgi Gerganov [Sat, 24 Jun 2023 16:39:32 +0000 (19:39 +0300)]
tests : allow to set threads to test-grad0
Borislav Stanimirov [Sat, 24 Jun 2023 16:11:35 +0000 (19:11 +0300)]
build : fix compilation errors and warnigns when building with MSVC (#275)
Borislav Stanimirov [Sat, 24 Jun 2023 16:06:13 +0000 (19:06 +0300)]
tests : increase stack size for test1 when building with MSVC (#277)
Georgi Gerganov [Sat, 24 Jun 2023 16:03:09 +0000 (19:03 +0300)]
tests : use LBFGS optimizer instead of ADAM (close #276)
ADAM seems to behave differently since the recent training changes.
Need to see how to make it work again for test2 - probably some
parameters need to be adjusted
AmbientL [Sat, 24 Jun 2023 15:31:38 +0000 (15:31 +0000)]
ggml : more verbose memory allocation failure (#270)
AmbientL [Sat, 24 Jun 2023 15:30:23 +0000 (15:30 +0000)]
starcoder : add special tokens for fill-in-the-middle task (#269)
Georgi Gerganov [Sat, 24 Jun 2023 15:27:46 +0000 (18:27 +0300)]
ggml : sync llama.cpp (tensor names)
Georgi Gerganov [Mon, 19 Jun 2023 18:28:16 +0000 (21:28 +0300)]
ci : reduce GGML_NLOOP to 3
Georgi Gerganov [Mon, 19 Jun 2023 17:43:19 +0000 (20:43 +0300)]
tests : sync test-grad0 from llama.cpp
Georgi Gerganov [Mon, 19 Jun 2023 17:43:12 +0000 (20:43 +0300)]
ggml : fix bug in LBFGS optimizer
Georgi Gerganov [Mon, 19 Jun 2023 17:35:08 +0000 (20:35 +0300)]
ggml : sync latest llama.cpp
Ebey Abraham [Sun, 18 Jun 2023 10:33:38 +0000 (11:33 +0100)]
gpt-2 : fix typo (#261)
Co-authored-by: Ebey Abraham <redacted>
Avi Lumelsky [Sun, 18 Jun 2023 10:32:09 +0000 (13:32 +0300)]
whisper : removed duplicate lines in convert-pt-to-ggml.py (#256)
Deleted 2 lines of .astype(float32) conversion to the model weights (No real impact, just for cleaner code)
Lukas Möller [Sun, 18 Jun 2023 08:34:21 +0000 (10:34 +0200)]
replit : update inference code to match reference (#218)
* Update replit inference code to match reference
* Add qntvr printf
Adam Tazi [Sun, 18 Jun 2023 08:15:58 +0000 (01:15 -0700)]
ci : introduce Github Actions CI workflow (#247)
* Introduce Github Actions CI workflow for the ggml repo
This commit integrates a Github Actions CI workflow that compiles and tests the codebase on both Ubuntu 22.04 and macOS 12 Monterey. The workflow is triggered on pull requests against the main branch and on every push to the main branch.
To accommodate the resource constraints of the Github-hosted runners, a `GGML_NITER` environment variable is introduced, allowing tests to run within a reasonable time frame. `test-grad0.c` is modified to use this variable instead of `GGML_NLOOP`.
The workflow file includes:
- A build strategy for both Ubuntu and MacOS.
- An environment setup with variables `GGML_NLOOP` and `GGML_NITER`.
- A step to limit the number of threads used by `test2.c` for efficient execution.
- A typical build process with steps for environment creation, CMake configuration, building, and verbose testing with a timeout.
* main to master
Tanmay [Sun, 18 Jun 2023 08:09:48 +0000 (13:39 +0530)]
ggml : convert interleaved addressing to sequential addressing for reduce functions (#117)
* Convert interleaved addressing to sequential addressing for REDUCE
* update addressing on new archs