vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-08 01:41:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
10523 commits 3 branches 237 tags 1.2 GiB
Commit graph

100 commits

Author SHA1 Message Date
Ruben Garcia
06d39dff73
Fix warnings (#1864) 2025-11-29 20:18:38 +08:00
Concedo
eda4a312cb Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/vulkan.Dockerfile
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/common.hpp
#	tests/test-backend-ops.cpp
#	tools/server/README.md
 2025-11-28 13:22:02 +08:00
Han Qingzhe
1d594c295c
clip: (minicpmv) fix resampler kq_scale (#17516) 
* debug:"solve minicpmv precision problem"

* “debug minicpmv”

* Apply suggestion from @ngxson

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
 2025-11-26 21:44:07 +01:00
LostRuins Concedo
3fe0e39b62 Merge commit '4dca015b7e' into concedo_experimental 
# Conflicts:
#	.github/copilot-instructions.md
#	README.md
#	docs/ops.md
#	docs/ops/CPU.csv
#	docs/ops/CUDA.csv
#	docs/ops/Vulkan.csv
#	ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
 2025-11-16 18:33:58 +08:00
Xuan-Son Nguyen
9b17d74ab7
mtmd: add mtmd_log_set (#17268) 2025-11-14 15:56:19 +01:00
Xuan-Son Nguyen
4b13a684c5
mtmd: fix patch_size initialized to random value in audio models (#17128) 
* mtmd: fix patch_size initialized to random value in audio models

* add default hparams
 2025-11-10 11:41:05 +01:00
LostRuins Concedo
df6e303fd3 merge https://github.com/ggml-org/llama.cpp/pull/17128 2025-11-10 11:24:04 +08:00
LostRuins Concedo
d02cb1b117 Revert "fix divide by zero error" 
This reverts commit 6cce98eca5.
 2025-11-10 11:22:50 +08:00
LostRuins Concedo
6cce98eca5 fix divide by zero error 2025-11-10 01:38:55 +08:00
LostRuins Concedo
60a74bdd89 make tool calling work with jinja. but still need to fix qwen omni first (+1 squashed commits) 
Squashed commits:

[e394da61e] make tool calling work with jinja. but still need to fix qwen omni first
 2025-11-09 16:56:14 +08:00
LostRuins Concedo
4fc022a51f revert qwen vl warmup size 2025-11-09 02:24:49 +08:00
LostRuins Concedo
d6a2ad8455 still not really working right 2025-11-09 01:57:48 +08:00
LostRuins Concedo
e6ca0aa8d0 Merge commit '2f0c2db43e' into concedo_experimental 
# Conflicts:
#	.github/labeler.yml
#	README.md
#	docs/backend/OPENCL.md
#	docs/ops.md
#	docs/ops/CUDA.csv
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/set_rows.tmpl.wgsl
#	scripts/sync-ggml.last
#	src/CMakeLists.txt
#	tools/server/README.md
 2025-11-08 23:27:59 +08:00
LostRuins Concedo
64a1cd95a7 fixed missing headers 2025-11-08 11:09:49 +08:00
LostRuins Concedo
dfb0966ed2 not working 2025-11-08 10:49:10 +08:00
LostRuins Concedo
fdcb281a3a Merge commit '2f966b8ed8' into concedo_experimental 
# Conflicts:
#	.github/workflows/release.yml
#	docs/docker.md
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-thread-safety.cpp
#	tools/batched-bench/batched-bench.cpp
#	tools/mtmd/clip.cpp
 2025-11-08 10:34:17 +08:00
LostRuins Concedo
7061cd1cc9 Merge commit 'e4a71599e5' into concedo_experimental 
# Conflicts:
#	CODEOWNERS
#	tools/mtmd/clip.cpp
 2025-11-08 10:28:49 +08:00
Xuan-Son Nguyen
4882f0ff78
clip: implement minicpm-v sinusoidal embd using GGML (#17036) 
* clip: implement minicpm-v sinusoidal embd using GGML

* fix repeat op
 2025-11-06 11:02:54 +01:00
Xuan-Son Nguyen
92bb84f775
mtmd: allow QwenVL to process larger image by default (#17020) 2025-11-05 14:26:49 +01:00
Xuan-Son Nguyen
2f0c2db43e
mtmd: improve struct initialization (#16981) 2025-11-05 11:26:37 +01:00
Xuan-Son Nguyen
070ff4d535
mtmd: add --image-min/max-tokens (#16921) 2025-11-03 11:11:18 +01:00
Xuan-Son Nguyen
bf7b0c9725
mtmd: pad mask for qwen2.5vl (#16954) 
* mtmd: pad mask for qwen2.5vl

* improve
 2025-11-03 10:25:55 +01:00
Zhiyong Wang
6b9a52422b
model: add Janus Pro for image understanding (#16906) 
* Add support for Janus Pro

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Address reviewer suggestions

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Add JANUS_PRO constant

* Update clip model handling

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

* Update tools/mtmd/clip.cpp

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

* Refactor JANUS_PRO handling in clip.cpp

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

* Update tools/mtmd/clip.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* em whitespace

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
 2025-11-02 22:08:04 +01:00
Georgi Gerganov
2f966b8ed8
clip : use FA (#16837) 
* clip : use FA

* cont : add warning about unsupported ops

* implement "auto" mode for clip flash attn

* clip : print more detailed op support info during warmup

* cont : remove obsolete comment [no ci]

* improve debugging message

* trailing space

* metal : remove stray return

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
 2025-11-02 21:21:48 +01:00
Concedo
af327857ec handle loading very old mmproj that broke after https://github.com/ggml-org/llama.cpp/pull/14928 2025-11-02 02:11:17 +08:00
Xuan-Son Nguyen
cf659bbb8e
mtmd: refactor preprocessing + support max/min pixels (#16878) 
* mtmd: refactor preprocessing + support max/min pixels

* fix mlp type

* implement mix/max pixels

* improve hparams

* better image preproc for qwen

* fix

* fix out of bound composite

* fix (2)

* fix token calculation

* get_merge_kernel_size()

* fix llama4 and lfm2

* gonna fix them all

* use simple resize for qwen

* qwen: increase min tokens

* no resize if dst size == src size

* restore to initial min/max tokens value for qwen
 2025-11-01 15:51:36 +01:00
Concedo
2b00e55356 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/docker.yml
#	ggml/src/ggml-opencl/kernels/mul_mm_f16_f32_l4_lm.cl
#	ggml/src/ggml-opencl/kernels/mul_mm_f32_f32_l4_lm.cl
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/rope.tmpl.wgsl
#	requirements/requirements-convert_legacy_llama.txt
#	tests/test-backend-ops.cpp
#	tests/test-rope.cpp
#	tools/server/README.md
 2025-10-31 10:52:57 +08:00
JJJYmmm
d261223d24
model: add support for qwen3vl series (#16780) 
* support qwen3vl series.

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>

* bugfix: fix the arch check for qwen3vl-moe.

* use build_ffn

* optimize deepstack structure

* optimize deepstack feature saving

* Revert "optimize deepstack feature saving" for temporal fix

This reverts commit f321b9fdf13e59527408152e73b1071e19a87e71.

* code clean

* use fused qkv in clip

* clean up / rm is_deepstack_layers for simplification

* add test model

* move test model to "big" section

* fix imrope check

* remove trailing whitespace

* fix rope fail

* metal : add imrope support

* add imrope support for sycl

* vulkan: add imrope w/o check

* fix vulkan

* webgpu: add imrope w/o check

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix tensor mapping

---------

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-10-30 16:19:14 +01:00
Tianyue-Zhao
bacddc049a
model: Add support for CogVLM model (#15002) 
* Added GGUF mappings for CogVLM model

* Add tensor mapping for CogVLM visual encoder

* Add CogVLM to conversion script, no vision part yet

* Added CogVLM vision model to conversion script

* Add graph for CogVLM CLIP model

* Add graph for CogVLM

* Fixes for CogVLM. Now compiles.

* Model now runs

* Fixes for cogvlm graph

* Account for graph context change after rebase

* Changes for whitespace

* Changes in convert script according to comments

* Switch CogVLM LLM graph to merged QKV tensor

* Use rope_type variable instead of direct definition

* Change CogVLM CLIP encoder to use SWIGLU

* Switch CogVLM CLIP to use merged QKV

* Apply rebase edits and remove ggml_cont call that is now unnecessary

* clean up

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
 2025-10-30 12:18:50 +01:00
Concedo
16cbe9f24e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	CODEOWNERS
#	docs/ops.md
#	docs/ops/SYCL.csv
#	examples/embedding/README.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	ggml/src/ggml-sycl/norm.hpp
#	scripts/snapdragon/adb/run-bench.sh
#	scripts/snapdragon/adb/run-cli.sh
#	src/llama-batch.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/llama-bench/README.md
 2025-10-30 13:44:46 +08:00
Concedo
472438aad3 Merge commit '5a4ff43e7d' into concedo_experimental 
# Conflicts:
#	docs/build.md
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	src/llama-context.cpp
#	tests/test-backend-ops.cpp
 2025-10-30 13:13:00 +08:00
Xuan-Son Nguyen
e1ab084803
mtmd : fix idefics3 preprocessing (#16806) 
* mtmd : fix idefics3 preprocessing

* disable granite test

* fix test for granite
 2025-10-27 23:12:16 +01:00
Xuan-Son Nguyen
c55d53acec
model : add LightOnOCR-1B model (#16764) 
* model : add LightOnOCR-1B model

* add test
 2025-10-27 16:02:58 +01:00
Concedo
85556118b5 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-cann/acl_tensor.cpp
#	ggml/src/ggml-cann/acl_tensor.h
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/element_wise.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/presets.hpp
 2025-10-18 10:56:55 +08:00
Xuan-Son Nguyen
1bb4f43380
mtmd : support home-cooked Mistral Small Omni (#14928) 2025-10-16 19:00:31 +02:00
Concedo
bb5cef1756 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/nix/package.nix
#	ci/run.sh
#	ggml/src/ggml-cpu/amx/amx.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/rms_norm.wgsl
#	tools/server/README.md
 2025-10-06 22:41:46 +08:00
Gabe Goodhart
ca71fb9b36
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206) 
* feat: Add granite-docling conversion using trillion pretokenizer

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add granite-docling vocab pre enum

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Use granite-docling pre

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add clip_is_idefics3

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Allow multi-token boundary sequences for image templating

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add tiling support for idefices3 in clip.cpp

This should likely be moved into llava_uhd::get_slice_instructions, but for
now this avoids disrupting the logic there.

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Partial support for full templating for idefics3 in mtmd

There are still errors encoding some of the image chunks, but the token
sequence now matches transformers _almost_ perfectly, except for the double
newline before the global image which shows up as two consecutive newline
tokens instead of a single double-newline token. I think this is happening
because the blocks are tokenized separately then concatenated.

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Fully working image preprocessing for idefics3 w/ resize and slicing

Branch: gabe-l-hart/GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Parse the preprocessor config's longest side and add it to the mmproj hparams

Branch: GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Use the longest side instead of size * scale_factor

For Granite Docling, these come out to the same value, but that was just a
conicidence.

Branch: GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Allow batch encoding and remove clip_is_idefics3

Branch: GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* refactor: Remove unnecessary conditionals for empty token vectors

Branch: GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* refactor: Use image_manipulation util

Branch: GraniteDocling

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* add test model

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
 2025-10-05 14:57:47 +02:00
Concedo
b120e107f9 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.clang-tidy
#	.devops/musa.Dockerfile
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	.gitignore
#	CODEOWNERS
#	CONTRIBUTING.md
#	README.md
#	build-xcframework.sh
#	ci/README-MUSA.md
#	ci/run.sh
#	common/CMakeLists.txt
#	docs/docker.md
#	examples/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/model-conversion/Makefile
#	examples/model-conversion/README.md
#	examples/model-conversion/logits.cpp
#	examples/model-conversion/scripts/causal/compare-logits.py
#	examples/model-conversion/scripts/causal/run-org-model.py
#	examples/model-conversion/scripts/embedding/compare-embeddings-logits.sh
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/check-nmse.py
#	examples/model-conversion/scripts/utils/inspect-org-model.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/CMakeLists.txt
#	ggml/include/ggml-zdnn.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/set_rows.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-tokenizers-repo.sh
#	tools/perplexity/perplexity.cpp
#	tools/server/tests/README.md
 2025-09-27 17:09:14 +08:00
Aleksei Nikiforov
cc1cfa277b
mtmd : fix uninitialized variable in bicubic_resize (#16275) 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
Co-authored-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-09-26 15:00:44 +02:00
Diego Devesa
50f4281a6f
llama : allow using iGPUs with --device (#15951) 
* llama : allow using iGPUs with --device

* mtmd : allow iGPU

* rpc-server : allow iGPU
 2025-09-13 16:49:49 +02:00
Concedo
575eb40950 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	docs/multimodal/minicpmv4.0.md
#	examples/model-conversion/Makefile
#	examples/model-conversion/README.md
#	examples/model-conversion/logits.cpp
#	examples/model-conversion/scripts/causal/modelcard.template
#	examples/model-conversion/scripts/utils/hf-create-model.py
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
#	tools/batched-bench/batched-bench.cpp
 2025-08-26 19:09:48 +08:00
Xuan-Son Nguyen
79a546220c
mtmd : support Kimi VL model (#15458)
Some checks failed
Python check requirements.txt / check-requirements (push) Has been cancelled
Details
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Details
Python Type-Check / pyright type-check (push) Has been cancelled
Details 
* convert : fix tensor naming conflict for llama 4 vision

* convert ok

* support kimi vision model

* clean up

* fix style

* fix calc number of output tokens

* refactor resize_position_embeddings

* add test case

* rename build fn

* correct a small bug
 2025-08-26 12:54:19 +02:00
tc-mb
c4e9239064
model : support MiniCPM-V 4.5 (#15575) 2025-08-26 10:05:55 +02:00
Concedo
8b8396c30c Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	README.md
#	docs/build-s390x.md
#	examples/llama.vim
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	scripts/compare-llama-bench.py
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
 2025-08-23 11:35:28 +08:00
Concedo
257992d6b8 possibly unstable, needs testing for fa 2025-08-22 17:35:32 +08:00
Tarek Dakhran
e288693669
readme : model : mtdm : lfm2 improvements (#15476) 
* Support untied embeddings

* Increase number of image tokens to 1024

* Add LFM2-VL to readme

* Actually use untied embeddings
 2025-08-22 09:29:08 +02:00
Michael Giba
b108e42904
ci : fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue (#15221) 
* Fix -Werror=return-type so ci/run.sh can run

* Update tools/mtmd/clip.cpp

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* Remove false now that we have abort

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2025-08-21 12:06:46 +02:00
Concedo
1c41c38a6a Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/cuda.Dockerfile
#	CODEOWNERS
#	README.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	scripts/sync-ggml.sh
#	tests/test-chat.cpp
#	tools/batched-bench/batched-bench.cpp
#	tools/mtmd/clip.h
 2025-08-20 20:34:45 +08:00
Concedo
140ae92886 Merge commit '65349f26f2' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
 2025-08-19 11:35:32 +08:00
Xuan-Son Nguyen
f08c4c0d8d
mtmd : clean up clip_n_output_tokens (#15391) 2025-08-18 22:53:52 +02:00