vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
7698 commits 3 branches 196 tags 386 MiB
Commit graph

128 commits

Author SHA1 Message Date
Concedo
db6db9dff9 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/server.yml
#	AUTHORS
#	CMakeLists.txt
#	Makefile
#	README.md
#	cmake/llama.pc.in
#	common/CMakeLists.txt
#	docs/build.md
#	examples/batched.swift/Sources/main.swift
#	examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
#	examples/llava/CMakeLists.txt
#	examples/llava/clip.h
#	examples/run/run.cpp
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-json-schema-to-grammar.cpp
 2025-02-07 00:52:31 +08:00
SAMI
1ec208083c
llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644) 
* Added quantization for visual projector
* Added README
* Fixed the clip quantize implementation in the file

* Fixed the gcc warning regarding minor linting

* Removed trailing whitespace
 2025-02-05 10:45:40 +03:00
piDack
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573) 
* add glm edge chat model

* use config partial_rotary_factor as rope ratio

* support for glm edge model

* vision model support

* remove debug info

* fix format

* llava.cpp trailing whitespace

* remove unused AutoTokenizer

* Update src/llama.cpp for not contain <|end|> or </s>

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* add edge template

* fix chat template

* fix confict

* fix confict

* fix ci err

* fix format err

* fix template err

* 9b hf chat support

* format

* format clip.cpp

* fix format

* Apply suggestions from code review

* Apply suggestions from code review

* Update examples/llava/clip.cpp

* fix format

* minor : style

---------

Co-authored-by: liyuhang <yuhang.li@zhipuai.cn>
Co-authored-by: piDack <pcdack@hotmail.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: liyuhang <yuhang.li@aminer.cn>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-02-02 09:48:46 +02:00
Concedo
70f1d8d746 vision can set max res (+1 squashed commits) 
Squashed commits:

[938fc655] vision can set max res
 2025-01-30 00:19:49 +08:00
Concedo
bec231422a Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/docker.md
#	examples/export-lora/export-lora.cpp
#	examples/main/README.md
#	examples/main/main.cpp
#	examples/run/README.md
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/simple-chat/simple-chat.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
 2025-01-25 14:16:50 +08:00
tc-mb
3e3357fd77
llava : support Minicpm-omni (#11289) 
* init

* add readme

* update readme

* no use make

* update readme

* update fix code

* fix editorconfig-checker

* no change convert py

* use clip_image_u8_free
 2025-01-22 09:35:48 +02:00
Concedo
e788b8289a You'll never take us alive 
We swore that death will do us part
They'll call our crimes a work of art
 2025-01-09 11:27:06 +08:00
Johannes Gäßler
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030) 
* GGUF: C++ refactor, backend support, misc fixes

remove ggml_tensor.backend

update CODEOWNERS [no ci]

remove gguf_get_data from API

revise GGUF API data types
 2025-01-07 18:01:58 +01:00
Concedo
b7d3274523 temporarily make qwenv2l use clip on cpu for vulkan and macos 2024-12-21 09:15:31 +08:00
Georgi Gerganov
d408bb9268
clip : disable GPU support (#10896) 
ggml-ci
 2024-12-19 18:47:15 +02:00
Concedo
fbf1345a66 clip quantize skip problematic layer 2024-12-19 16:25:48 +08:00
Concedo
ee486bad3e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
#	examples/CMakeLists.txt
#	examples/batched/batched.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama.android/llama/build.gradle.kts
#	examples/main/README.md
#	examples/retrieval/retrieval.cpp
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml.c
#	scripts/compare-commits.sh
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-sampling.cpp
 2024-12-19 11:57:43 +08:00
Georgi Gerganov
0bf2d10c55
tts : add OuteTTS support (#10784) 
* server : add "tokens" output

ggml-ci

* server : output embeddings for all tokens when pooling = none

ggml-ci

* server : be explicit about the pooling type in the tests

ggml-ci

* server : do not normalize embeddings when there is no pooling

ggml-ci

* llama : add OuteTTS support (wip)

* wip

* extract features

* first conv

* group norm

* resnet conv

* resnet

* attn

* pos net

* layer norm

* convnext

* head

* hann window

* fix n_embd + remove llama.cpp hacks

* compute hann window

* fft

* spectrum processing

* clean-up

* tts : receive input text and generate codes

* clip : fix new conv name

* tts : minor fix

* tts : add header + minor fixes

ggml-ci

* tts : add matchematical constant

ggml-ci

* tts : fix sampling + cut initial noise

* tts : fixes

* tts : update default samplers

ggml-ci

* tts : text pre-processing

* tts : outetts-voc -> wavtokenizer-dec

* tts : remove hardcoded constants

ggml-ci

* tts : fix tensor shapes

* llama : refactor wavtokenizer tensors

ggml-ci

* cont

ggml-ci

* cont [no ci]

* llama : update WavTokenizer to non-causal attn

* llama : handle no-vocab detokenization

* tts : add Python example for OuteTTS (wip)

* tts : extend python example to generate spectrogram

ggml-ci

* server : fix rebase artifacts

* tts : enable "return_tokens" in Python example

ggml-ci

* tts : minor fixes

* common : support HF download for vocoder
 2024-12-18 19:27:21 +02:00
Concedo
f456ed7237 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/nix/package.nix
#	.devops/tools.sh
#	.github/workflows/build.yml
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	common/common.h
#	examples/llava/CMakeLists.txt
#	examples/run/CMakeLists.txt
#	examples/run/README.md
#	examples/run/run.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-kompute/ggml-kompute.cpp
#	tests/test-backend-ops.cpp
#	tests/test-rope.cpp
 2024-12-15 15:30:10 +08:00
HimariO
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361) 
* Barebone Qwen2VL LLM convertor

* Add Qwen2VL cli entrypoint

* [WIP] add qwen2vl arch

* Verify m-rope output

* Add vl-rope/2d-rope support for qwen2vl ViT

* update qwen2vl cli tool

* update 5D tensor op workaround

* [WIP] qwen2vl vision model

* make batch and clip utils compatible with qwen2vl

* [WIP] create inference workflow, gguf convert script but fix

* correcting vision-rope behavior, add the missing last layer back to ViT

* add arg parser to qwen2vl_surgery

* replace variable size array with vector

* cuda-gdb cmake preset

* add fp32 mrope, vision rope kernel

* add fp16 support for qwen2vl and m-rope

* add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION`

* fix rope op mode switching, out dated func args

* update `llama_hparams`

* update to keep up stream changes

* resolve linter, test errors

* add makefile entry, update speical image padding token

* add mrope unit test, fix few compiler warnings

* rename `mrope` related function, params

* minor updates on debug util, bug fixs

* add `m-rope` testcase to `test-backend-ops`

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* fix traililng whitespce

* store `llama_hparams.rope_sections` with fixed size array

* update position id tensor size check in GGML_OP_ROPE

* minor updates

* update `ggml_backend_*_supports_op` of unsupported backends

* remote old `rope_section` compare operator

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-12-14 14:43:46 +02:00
Concedo
4c4ce5e808 rewritten checkpoint 1 - before coopmat 2024-12-13 16:55:23 +08:00
piDack
01e6d9bb71
clip : add sycl support (#10574) 
Co-authored-by: piDack <pcdack@hotmail.co>
 2024-12-04 01:26:37 +01:00
Concedo
697ca70115 temp checkpoint 2024-11-30 12:13:20 +08:00
Ting Lou
678d7994f4
llava: return false instead of exit (#10546) 2024-11-29 01:09:46 +01:00
Concedo
bb13925f39 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	CMakePresets.json
#	Makefile
#	Package.swift
#	ci/run.sh
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	flake.lock
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml.c
#	pocs/vdot/q8dot.cpp
#	pocs/vdot/vdot.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-rope.cpp
 2024-11-04 16:54:53 +08:00
Diego Devesa
9f40989351
ggml : move CPU backend to a separate file (#10144) 2024-11-03 19:34:08 +01:00
Concedo
ce7f9c9a2c Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/python-type-check.yml
#	CMakeLists.txt
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	examples/embedding/embedding.cpp
#	examples/server/README.md
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/ggml.c
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/sync-ggml.last
#	src/llama-vocab.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-tokenizer-0.cpp
 2024-10-02 01:00:57 +08:00
Georgi Gerganov
cad341d889
metal : reduce command encoding overhead (#9698) 
* metal : reduce command encoding overhead

ggml-ci

* metal : add comments
 2024-10-01 16:00:25 +03:00
Concedo
29625c3d2e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	ci/run.sh
#	common/CMakeLists.txt
#	common/common.cpp
#	docs/backend/SYCL.md
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/infill/infill.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/main/README.md
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	examples/server/bench/README.md
#	examples/server/tests/README.md
#	examples/speculative/speculative.cpp
#	flake.lock
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	grammars/README.md
#	scripts/compare-commits.sh
#	scripts/compare-llama-bench.py
#	tests/CMakeLists.txt
 2024-09-19 14:53:57 +08:00
Georgi Gerganov
6262d13e0b
common : reimplement logging (#9418) 
https://github.com/ggerganov/llama.cpp/pull/9418
 2024-09-15 20:46:12 +03:00
Concedo
e44ddf26ef Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	Makefile
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/llava/MobileVLM-README.md
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/quantize/CMakeLists.txt
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	tests/test-backend-ops.cpp
 2024-09-13 16:17:24 +08:00
Georgi Gerganov
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408) 
* ggml : hide ggml_object, ggml_cgraph, ggml_hash_set

ggml-ci

* ggml : add ggml-impl.h to backends

* ggml : fix compiler warnings

ggml-ci

* ggml : add assert upon adding nodes
 2024-09-12 14:23:49 +03:00
Concedo
b6f9aaa9ab Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	docs/backend/SYCL.md
 2024-08-30 20:25:34 +08:00
tc-mb
7ea8d80d53
llava : the function "clip" should be int (#9237) 2024-08-30 07:21:57 +02:00
Concedo
b2c1ff7a13 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.ecrc
#	CMakePresets.json
#	ci/run.sh
#	docs/backend/SYCL.md
#	ggml/src/CMakeLists.txt
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-sampling.cpp
 2024-08-27 17:46:40 +08:00
Justine Tunney
436787f170
llama : fix time complexity of string replacement (#9163) 
This change fixes a bug where replacing text in a very long string could
cause llama.cpp to hang indefinitely. This is because the algorithm used
was quadratic, due to memmove() when s.replace() is called in a loop. It
seems most search results and LLM responses actually provide the O(n**2)
algorithm, which is a great tragedy. Using a builder string fixes things
 2024-08-26 09:09:53 +03:00
Concedo
c61fa9155d handle oversized images by downscaling 2024-08-26 13:58:18 +08:00
Concedo
7bc87e1f0f added llava letterboxing feature 2024-08-25 23:15:38 +08:00
fairydreaming
f63f603c87
llava : zero-initialize clip_ctx structure fields with aggregate initialization 908) 
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
 2024-08-21 09:45:49 +02:00
Changyeon Kim
2f3c1466ff
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984) 
* llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model.

- The CLIP model now prioritizes the Vulkan backend over the CPU when vulkan available.
- A GGML_OP_ACC shader has been added.
- The encoding performance of the CLIP model improved from 4.2s on the CPU to 0.9s on the GPU.

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>

* fix-up coding style.

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>

* Fix-up the missing initial parameter to resolve the compilation warning.

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>

* [fix] Add missing parameters.

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>

* [fix] Use nb1 and nb2 for dst.

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>

* Fix check results ggml_acc call

---------

Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
Co-authored-by: 0cc4m <picard12@live.de>
 2024-08-20 21:00:00 +02:00
tc-mb
d565bb2fd5
llava : support MiniCPM-V-2.6 (#8967) 
* init

* rename

* add run android for termux in readme

* add android readme

* add instructions in readme

* change name in readme

* Update README.md

* fixed line

* add result in readme

* random pos_embed

* add positions index

* change for ollama

* change for ollama

* better pos_embed in clip

* support ollama

* updata cmakelist

* updata cmakelist

* rename wrapper

* clear code

* replace and organize code

* add link

* sync master

* fix warnings

* fix warnings

* fix bug in bicubic resize when need resize iamge smaller

* receive review comments and modify

* receive review comments and modify

* put all code into llava dir

* fix quality problem in pr code

* change n_layer

* add space in "-1"

* imitate reshape bug of python code

* fix bug in clip

* fix issues for merging

* fix llama-minicpmv-cli in cmake file

* change pr readme

* fix code review

* remove in line 33 directory in the /cmakelists.txt (not in example, in the main dir

* fix cmakefile

* add warn

* fix KEY_HAS_MINICPMV_PROJ

* remove load_image_size into clip_ctx

* remove the extern "C", MINICPMV_API

* fix uhd code for review comment

* delete minicpmv-wrapper in pr

* remove uhd_image_embed

* Modify 2 notes

* support minicpmv2.6

* modify convert script of minicpmv

* modify convert

* modify convert

* add readme

* add resampler of v2.6

* modify clip

* modify readme

* fix type-check

* fix type-check

* fix type-check

* fix type-check

* modify convert script and readme

* fix convert script and readme

* fix convert

* fix num in convert

* fix type-check

---------

Co-authored-by: Hongji Zhu <fireyoucan@gmail.com>
Co-authored-by: harvestingmoon <leewenyeong@gmail.com>
 2024-08-16 16:34:41 +03:00
Georgi Gerganov
45a55b91aa
llama : better replace_all (cont) (#8926) 
* llama : better replace_all (cont)

ggml-ci

* code : deduplicate replace_all

ggml-ci
 2024-08-09 18:23:52 +03:00
tc-mb
3071c0a5f2
llava : support MiniCPM-V-2.5 (#7599) 
* init

* rename

* add run android for termux in readme

* add android readme

* add instructions in readme

* change name in readme

* Update README.md

* fixed line

* add result in readme

* random pos_embed

* add positions index

* change for ollama

* change for ollama

* better pos_embed in clip

* support ollama

* updata cmakelist

* updata cmakelist

* rename wrapper

* clear code

* replace and organize code

* add link

* sync master

* fix warnings

* fix warnings

* fix bug in bicubic resize when need resize iamge smaller

* receive review comments and modify

* receive review comments and modify

* put all code into llava dir

* fix quality problem in pr code

* change n_layer

* add space in "-1"

* imitate reshape bug of python code

* fix bug in clip

* fix issues for merging

* fix llama-minicpmv-cli in cmake file

* change pr readme

* fix code review

* remove in line 33 directory in the /cmakelists.txt (not in example, in the main dir

* fix cmakefile

* add warn

* fix KEY_HAS_MINICPMV_PROJ

* remove load_image_size into clip_ctx

* remove the extern "C", MINICPMV_API

* fix uhd code for review comment

* delete minicpmv-wrapper in pr

* remove uhd_image_embed

* Modify 2 notes

* clip : style changes

* del common.h in clip

* fix Type-Check error

* fix Type-Check error

* fix Type-Check error

* fix Type-Check error

* fix makefile error

* fix ubuntu-make error

* try fix clip

* try fix 1

---------

Co-authored-by: Hongji Zhu <fireyoucan@gmail.com>
Co-authored-by: harvestingmoon <leewenyeong@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-08-09 13:33:53 +03:00
slaren
2b1f616b20
ggml : reduce hash table reset cost (#8698) 
* ggml : reduce hash table reset cost

* fix unreachable code warnings after GGML_ASSERT(false)

* GGML_ASSERT(false) -> GGML_ABORT("fatal error")

* GGML_ABORT use format string
 2024-07-27 04:41:55 +02:00
hipudding
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035) 
* [CANN] Add Ascend NPU backend

Ascend is a full-stack AI computing infrastructure for industry
applications and services based on Huawei Ascend processors and
software.

CANN (Compute Architecture of Neural Networks), developped by
Huawei, is a heterogeneous computing architecture for AI.

Co-authored-by: wangshuai09 <391746016@qq.com>

* delete trailing whitespaces

* Modify the code based on review comment

* Rename LLAMA_CANN to GGML_CANN

* Make ggml-common.h private

* add ggml_cann prefix for acl funcs

* Add logging for CANN backend

* Delete Trailing whitespace

---------

Co-authored-by: wangshuai09 <391746016@qq.com>
 2024-07-17 14:23:50 +03:00
Daniel Bevenius
9b31a40c6d
clip : suppress unused variable warnings (#8105) 
* clip : suppress unused variable warnings

This commit suppresses unused variable warnings for the variables e in
the catch blocks.

The motivation for this change is to suppress the warnings that are
generated on Windows when using the MSVC compiler. The warnings are
not displayed when using GCC because GCC will mark all catch parameters
as used.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! clip : suppress unused variable warnings

Remove e (/*e*/) instead instead of using GGML_UNUSED.

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
 2024-06-27 01:50:09 +02:00
Andrei
d11afd6652
llava : fix moondream support (#7163) 
* Revert "Revert "llava : add support for moondream vision language model (#6899)""

This reverts commit 9da243b36a.

* Fix num_positions and embeddings initialization
 2024-05-10 09:41:10 +03:00
Georgi Gerganov
9da243b36a
Revert "llava : add support for moondream vision language model (#6899)" 
This reverts commit 46e12c4692.
 2024-05-08 22:14:39 +03:00
vik
46e12c4692
llava : add support for moondream vision language model (#6899) 
* add support for moondream vision language model

This required making the following changes to the CLIP model:

1. Support for patch embedding bias.
2. Make class embedding and pre-layernorm optional.
3. Add support for post-layernorm.

* Update examples/llava/clip.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-04-25 22:38:31 +03:00
Daniel Bevenius
4ab99d8d47
clip : rename lerp function to avoid conflict (#6894) 
This commit renamesthe lerp (linear interpolation) function in clip.cpp
to avoid a conflict with the lerp function in the <cmath> standard C++
library when using c++20.

The motivation for this change is to enable projects that use c++20 to
be able to compile clip.cpp without having to resort to patching it. The
lerp function was added to cmath in version C++20 (202002L) and is why
this is not causing any issue at the moment as C++11/C++17 is currently
used by llama.cpp.

I realize that llama.cpp uses either C++11 (or C++17 in the case for
SYCL) but wanted to ask if this would be an acceptable change just the
same.

Refs: https://en.cppreference.com/w/cpp/numeric/lerp

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
 2024-04-25 15:38:14 +03:00
Justine Tunney
89b0bf0d5d
llava : use logger in llava-cli (#6797) 
This change removes printf() logging so llava-cli is shell scriptable.
 2024-04-21 15:19:04 +03:00
Ziang Wu
66ba560256
llava : fix MobileVLM (#6364) 
* fix empty bug

* Update MobileVLM-README.md

added more results on devices

* Update MobileVLM-README.md

* Update MobileVLM-README.md

* Update MobileVLM-README.md

* Update MobileVLM-README.md

* Update MobileVLM-README.md

* Update MobileVLM-README.md

* Update examples/llava/MobileVLM-README.md

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update MobileVLM-README.md

remove gguf links

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-03-28 16:33:10 +02:00
slaren
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299) 2024-03-26 01:16:01 +01:00
Ziang Wu
272935b281
llava : add MobileVLM_V2 backup (#6175) 
* Add MobileVLM_V2 backup

* Update MobileVLM-README.md

* Update examples/llava/MobileVLM-README.md

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/llava/convert-image-encoder-to-gguf.py

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* clip :  fix whitespace

* fix deifinition mistake in clip.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-03-20 17:02:32 +02:00
Georgi Gerganov
d795988d9e
Revert "llava : add a MobileVLM_V2-1.7B backup (#6152)" 
This reverts commit f8c4e745e1.
 2024-03-20 13:29:49 +02:00