vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-20 09:25:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
13344 commits 3 branches 240 tags 1.3 GiB
Commit graph

296 commits

Author SHA1 Message Date
Concedo
9203b6a051 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/server.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui-ci.yml
#	.github/workflows/ui-publish.yml
#	.gitignore
#	CMakeLists.txt
#	CODEOWNERS
#	scripts/ui-download.cmake
#	scripts/xxd.cmake
#	tests/test-backend-ops.cpp
#	tests/test-reasoning-budget.cpp
#	tools/CMakeLists.txt
#	tools/server/CMakeLists.txt
#	tools/server/README.md
 2026-05-16 22:56:33 +08:00
Xuan-Son Nguyen
72e60f500d
mtmd: add chunks and fix preproc for qwen3a (#23073) 
* mtmd: add chunks and fix preproc for qwen3a

* add attn_mask

* limit mtmd_chunk size (avoid blow up memory)

* correct audio tokens

* re-order the set_input case

* remove attn_mask
 2026-05-15 19:32:47 +02:00
Concedo
cc82c3164e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/intel.Dockerfile
#	.github/workflows/build-cross.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/release.yml
#	cmake/riscv64-spacemit-linux-gnu-gcc.cmake
#	docs/backend/OPENVINO.md
#	docs/backend/SYCL.md
#	docs/build-riscv64-spacemit.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	embd_res/ggml-vocab-qwen35.gguf
#	embd_res/ggml-vocab-qwen35.gguf.inp
#	embd_res/ggml-vocab-qwen35.gguf.out
#	examples/model-conversion/Makefile
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/common.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_reduce.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	ggml/src/ggml-zendnn/CMakeLists.txt
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	scripts/snapdragon/adb/run-completion.sh
#	tests/CMakeLists.txt
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/clip-impl.h
#	tools/mtmd/clip.cpp
#	tools/mtmd/clip.h
#	tools/server/README.md
 2026-05-14 19:04:04 +08:00
Georgi Gerganov
67b2b7f2f2
logs : reduce (#23021)
Some checks failed
Python Type-Check / python type-check (push) Waiting to run
Details
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Details
Python check requirements.txt / check-requirements (push) Has been cancelled
Details
Update Operations Documentation / update-ops-docs (push) Has been cancelled
Details 
* logs : reduce

* args : fix envs

* server : fix build

* common : print verbosity level at start

* server : clean-up logs

* server : print prompt processing timings + sampling params

* minor : whitespaces
 2026-05-14 13:05:52 +03:00
Xuan-Son Nguyen
7bfe120c21
mtmd, server, common: expose modalities to /v1/models (#22952) 
* mtmd, server, common: expose modalities to /v1/models

* fix build

* rename to mtmd_caps
 2026-05-12 19:08:07 +02:00
Concedo
f7923b261f need to fix cuda compile. Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/python-type-check.yml
#	examples/speculative-simple/README.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-cuda/im2col.cu
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
 2026-05-12 20:47:07 +08:00
AesSedai
4178259130
mtmd: add MiMo v2.5 vision (#22883) 
* mimo-v2.5: vision support

* mimo-v2.5: use fused qkv for vision

* mimi-v2.5: fix f16 vision overflow

* mimo-v2.5: comment cleanups

* mimo-v2.5: Flash doesn't have mmproj
more cleanup
remember to use filter_tensors

* mimo-v2.5: fix trailing whitespace
 2026-05-12 11:11:14 +02:00
Concedo
eb30b29d69 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/gguf-publish.yml
#	CODEOWNERS
#	examples/sycl/test.sh
#	pyproject.toml
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/README.md
 2026-05-08 14:48:57 +08:00
Pascal
cc97e45a14
mtmd: fix whisper audio tail truncation by exposing padded buffer to FFT (#22770) 2026-05-07 14:01:01 +02:00
tc-mb
2496f9c149
mtmd : support MiniCPM-V 4.6 (#22529) 
* Support MiniCPM-V 4.6 in new branch

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix code bug

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix pre-commit

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix convert

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* rename clip_graph_minicpmv4_6

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* use new TYPE_MINICPMV4_6

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* use build_attn to allow flash attention support

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* no use legacy code, restored here.

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* use the existing tensors name

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* unused ctx->model.hparams.minicpmv_version

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* use n_merge for slice alignment

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* borrow wa_layer_indexes for vit_merger insertion point

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix code style

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* Update convert_hf_to_gguf.py

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

* use filter_tensors and add model.vision_tower

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix chkhsh

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix type check

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

---------

Signed-off-by: tc-mb <tianchi_cai@icloud.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-05-06 21:54:09 +02:00
Concedo
9e9497f0cc Merge remote-tracking branch 'origin/upstream' into concedo_experimental 
# Conflicts:
#	examples/save-load-state/save-load-state.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemm_noshuffle_q4_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemm_noshuffle_q8_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32_spec.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q8_0_f32.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	scripts/sync-ggml.last
#	scripts/sync_vendor.py
#	src/llama-graph.cpp
#	tests/test-backend-ops.cpp
#	tests/test-state-restore-fragmented.cpp
 2026-05-06 21:20:06 +08:00
Yakine Tahtah
a00e47e422
mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech) (#22101) 
* mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech)

Conformer encoder with Shaw relative position encoding,
QFormer projector, log-mel spectrogram with frame stacking.

Encoder uses GLU gating, folded batch norm, and SSM depthwise
conv. QFormer compresses encoder output via windowed
cross-attention (window=15, queries=3) into the LLM embedding
space.

Audio preprocessing: reflect-padded STFT, 80-bin mel filterbank,
dynamic range compression, 2x frame stacking (80->160 mel).

GGUF converter handles batch norm folding at export time,
fused K/V split, and Conv1d weight reshaping.

Tested against HF transformers reference: token-for-token match
on 30s/60s audio clips with greedy decoding.

* mtmd: rename gs_ prefixed tensors to generic/architecture names

* mtmd: use tensor_mapping.py for all granite_speech tensors

* convert: fold GraniteSpeechTextModel into GraniteModel

* mtmd: replace n_layer hack with explicit has_standard_layers flag

* mtmd: replace hardcoded magic numbers with GGUF hparams for granite speech

* mtmd: align KEY_A_ define spacing

* convert: register GraniteModel for GraniteSpeechForConditionalGeneration

* convert: fix ty type-check for GraniteSpeechMmprojModel registration

* mtmd: align TN_ define spacing

* mtmd: use generic layer loop for granite speech tensor loading

* mtmd: merge qformer_proj_layer into clip_layer

* mtmd: granite_speech remove redundant ggml_build_forward_expand on inputs

* mtmd: granite_speech add comment explaining why build_attn is not used

* mtmd: granite_speech hard-code eps in cpp, remove from GGUF metadata

* gguf: add spacing between granite_speech tensor mapping blocks

* mtmd: make generic audio layer_norm_eps read optional

* mtmd: granite_speech keep encoder eps in GGUF, only hard-code projector eps

* mtmd: align defines and struct fields in clip-impl.h and clip-model.h

* mtmd: fix alignment and ordering issues across granite speech files

* convert: granite_speech use filter_tensors instead of modify_tensors for skipping
 2026-05-06 14:40:59 +02:00
Adrien Gallouët
bf76ac77be
common : only load backends when required (#22290) 
* common : only load backends when required

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* llama : call ggml_backend_load_all() directly from llama_backend_init()

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add ggml_backend_load_all() where llama_backend_init() is not used

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
 2026-05-05 09:23:50 +02:00
Concedo
70be589894 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	CODEOWNERS
#	examples/debug/debug.cpp
#	examples/eval-callback/eval-callback.cpp
#	ggml/src/ggml-cpu/amx/mmq.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	scripts/pr2wt.sh
 2026-04-28 21:13:40 +08:00
Max Krasnyansky
5594d13224
common: fix missing exports in llama-common (#22340) 
* common: refactor common/debug to move abort_on_nan into base_callback_data

Passing bool abort_on_nan as template parameter for common_debug_cb_eval is unnecessary and creates an issue with LTO.
It should just be a member of the base_callback_data instead.

* cont : cleanup

* common : use pimpl in debug.h to reduce header dependencies

Move common_debug_cb_user_data's data members (std::regex,
std::vector<uint8_t>) into a private impl struct in debug.cpp.

This removes the includes of common.h and <regex> from debug.h,
reducing transitive dependencies for any translation unit that
includes the header.

Assisted-by: llama.cpp:local pi

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2026-04-27 08:06:39 +03:00
Concedo
0755f27372 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/openvino.Dockerfile
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build.yml
#	common/chat.cpp
#	docs/backend/OPENVINO.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/libggml-htp.inf
#	ggml/src/ggml-openvino/ggml-decoder.cpp
#	ggml/src/ggml-openvino/ggml-openvino-extra.cpp
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-openvino/ggml-quants.cpp
#	ggml/src/ggml-openvino/openvino/op/rope.cpp
#	ggml/src/ggml-openvino/openvino/op_table.cpp
#	ggml/src/ggml-openvino/openvino/op_table.h
#	ggml/src/ggml-openvino/openvino/translate_session.cpp
#	ggml/src/ggml-openvino/openvino/utils.cpp
#	ggml/src/ggml-openvino/openvino/utils.h
#	ggml/src/ggml-openvino/utils.cpp
#	ggml/src/ggml-openvino/utils.h
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/convert.hpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/CMakeLists.txt
 2026-04-23 00:55:05 +08:00
Concedo
becf70d49b fixed logspam for fit 2026-04-23 00:43:09 +08:00
Xuan-Son Nguyen
82d3f4d3b2
mtmd: also support LLAMA_ROPE_TYPE_NONE (#22242) 2026-04-22 12:16:29 +02:00
manayang
7bfe60fdf9
mtmd, llama : Update HunyuanVL vision-language model support (#22037) 
* mtmd, llama : add HunyuanVL vision-language model support

- add LLM_ARCH_HUNYUAN_VL with M-RoPE (XD-RoPE) support
- add PROJECTOR_TYPE_HUNYUANVL with PatchMerger vision encoder
- add HunyuanVL-specific M-RoPE position encoding for image tokens
- add GGUF conversion for HunyuanVL vision and text models
- add smoke test in tools/mtmd/tests.sh

* fix: fix HunyuanVL XD-RoPE h/w section order

* fix: Remove redundant code

* convert : fix HunyuanOCR / HunyuanVL conversion
 - Tested locally: both HunyuanOCR and HunyuanVL-4B convert to GGUF
 - successfully and produce correct inference output on Metal (F16 / Q8_0).

* clip : fix -Werror=misleading-indentation in bilinear resize

* fix CI: convert_hf_to_gguf type check error
 - convert_hf_to_gguf.py: give HunyuanVLTextModel.__init__ an explicit `dir_model: Path` parameter so ty can infer the type for load_hparams instead of reporting `Unknown | None`.

---------

Co-authored-by: wendadawen <wendadawen@tencent.com>
 2026-04-22 11:58:43 +02:00
Kwa Jie Hao
98d2d2884e
mtmd: Add support for Reka Edge 2603 (#21616) 
* feat: (vocab) fix stray text appended in llama_decode_text

Remove accidental concatenation of the full `text` string when
formatting UNK_BYTE hex escapes. Only the closing "]" should be appended.

* feat(mtmd): add Yasa2 vision encoder support

Add a Yasa2 (ConvNeXtV2-based) vision encoder for reka-edge:
- Register PROJECTOR_TYPE_YASA2 and tensor name definitions
- Add yasa2_block/yasa2_stage model structs
- Implement graph builder with ConvNeXt stages, GRN, adaptive pooling
- Wire into clip.cpp switch statements and mtmd.cpp init_vision
- Use mtmd_image_preprocessor_fixed_size for image preprocessing

* feat(chat): add reka-edge template handler (tools, thinking)

- Add chat-reka.cpp/h implementing PEG-based parser for reka-edge format
- Add Reka-Edge.jinja chat template
- Detect reka-edge template in try_specialized_template()
- Add LLAMA_EXAMPLE_MTMD to chat-template-file arg

* feat: add reka vlm to gguf conversion script

Converts Reka Yasa2 hf checkpoints to GGUF format:
- Text decoder: Llama-arch with tiktoken/BPE vocab
- Mmproj (--mmproj): ConvNeXt vision backbone + language_projection
- Generates 2D sincos positional embeddings for vision encoder

* test: add Reka Edge chat template and parser tests

- test-chat-template: oracle tests comparing Jinja engine output vs
  common_chat_templates_apply for text, tools, thinking, images, video
- test-chat: PEG parser tests for Reka Edge format, round-trip tests
  for image/video content parts, common path integration tests

* scripts: add Reka Edge mixed quantization helper

Q4_0 base quantization with Q8_0 override for the last 8 transformer
blocks (layers 24-31) via --tensor-type regex.

* fix: adapt chat-reka and tests to upstream API

- Use autoparser::generation_params (not templates_params)
- Add p.prefix(generation_prompt) to PEG parser
- Simplify reasoning parser to match LFM2 pattern
- Remove image/video oracle tests (unsupported by oaicompat parser;
  no other multimodal models test this path)

* fix: avoid duplicate tensor loading in yasa2 vision encoder

TN_YASA_PATCH_W and TN_PATCH_EMBD both resolve to "v.patch_embd.weight",
causing the same tensor to be loaded twice into ctx_data and overflowing
the memory pool. Reuse the tensors already loaded by the common section.

* chore: update image pre-processing settings

The reka-edge model depends on the following settings in an older
fork of llama.cpp:
1. Fixed square resize
2. BICUBIC
3. add_padding=false

In current llama.cpp, this means setting:
- image_resize_algo = RESIZE_ALGO_BICUBIC
- image_resize_pad = false

* chore: remove reka gguf conversion script

* chore: remove reka quantization script

* chore: remove unnecessary changes from PR scope

This commit removes a couple of unnecessary changes for the PR scope:
1. BPE decoder bug fix - this affects reka edge because there's a bug
in our tokenization that doesn't represent <think> tokens as special
tokens. However this isn't meant to be a thinking model so when run
with --reasoning off the edge case does not affect us

2. --chat-template-file support from llama-mtmd-cli - the focus is on
llama-server and the reka edge gguf contains the necessary metadata
to detect the chat template

3. reka edge oracle test cases - no other model has similar test cases,
so I removed it for standardization

* chore: remove unnecessary ggml_cast

This commit removes unnecessary ggml_cast after updating the
reka vlm -> gguf conversion script on hugging face.

* chore: remove redundant code

* chore: remove unnecessary ggml_cont calls

This commit removes all ggml_cont calls except the four that
precede ggml_reshape_3d/ggml_reshape_4d. Those are necessary
because ggml_reshape recomputes strides assuming contiguous
layout and asserts ggml_is_contiguous.

Other operations (ggml_mean, ggml_add, ggml_mul etc.) use
stride-based indexing and handle non-contiguous inputs
correctly and so we are ok to remove ggml_cont for those.

* chore: remove unnecessary ggml_repeat calls

This commit removes unnecessary ggml_repeat calls because the underlying
ops already broadcast automatically.

Every ggml_repeat in yasa2.cpp was expanding a smaller tensor to match
a larger one's shape before passing both to an elementwise op (ggml_add,
ggml_sub, ggml_mul, or ggml_div). This is unnecessary because all four
of these ops already support broadcasting internally.

* chore: restore ggml_cont needed for cpu operations

* refactor: locate reka chat template handler in chat.cpp

* chore: remove unnecessary warmup tokens

* chore: add code comments on image_resize_pad

* chore: remove custom reka parsing code

* chore: revert common/chat.cpp

* Uncomment debug logging for PEG input parsing

---------

Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
 2026-04-21 20:02:49 +02:00
Concedo
4629b49afb updated to handle changes for clip_is_mrope 2026-04-21 19:34:32 +08:00
Concedo
19a12bb080 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	CODEOWNERS
#	common/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	scripts/sync-ggml.last
#	tools/cli/cli.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp
 2026-04-21 18:53:03 +08:00
Xuan-Son Nguyen
9998d88bc8
mtmd: correct mtmd_decode_use_mrope() (#22188) 2026-04-21 10:53:37 +02:00
Xuan-Son Nguyen
86f8daacfe
mtmd: correct get_n_pos / get_decoder_pos (#22175) 2026-04-20 23:29:19 +02:00
Xuan-Son Nguyen
a678916623
mtmd: refactor mtmd_decode_use_mrope (#22161) 2026-04-20 14:45:11 +02:00
Concedo
cd6788007e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-cross.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	examples/llama.android/lib/src/main/cpp/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync_vendor.py
#	tests/test-chat.cpp
#	tests/test-mtmd-c-api.c
#	tools/server/README.md
 2026-04-20 20:19:11 +08:00
Xuan-Son Nguyen
19124078be
mtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos (breaking change) (#22082) 
* mtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos

* fix build
 2026-04-19 11:57:21 +02:00
Concedo
79882d669a Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-android.yml
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	CODEOWNERS
#	common/CMakeLists.txt
#	common/common.h
#	docs/ops.md
#	docs/ops/Metal.csv
#	examples/batched/CMakeLists.txt
#	examples/convert-llama2c-to-ggml/CMakeLists.txt
#	examples/debug/CMakeLists.txt
#	examples/diffusion/CMakeLists.txt
#	examples/embedding/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/gen-docs/CMakeLists.txt
#	examples/idle/CMakeLists.txt
#	examples/lookahead/CMakeLists.txt
#	examples/lookup/CMakeLists.txt
#	examples/parallel/CMakeLists.txt
#	examples/passkey/CMakeLists.txt
#	examples/retrieval/CMakeLists.txt
#	examples/save-load-state/CMakeLists.txt
#	examples/speculative-simple/CMakeLists.txt
#	examples/speculative/CMakeLists.txt
#	examples/sycl/CMakeLists.txt
#	examples/training/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	pocs/vdot/CMakeLists.txt
#	src/CMakeLists.txt
#	tests/CMakeLists.txt
#	tests/test-quantize-stats.cpp
#	tools/batched-bench/CMakeLists.txt
#	tools/cli/CMakeLists.txt
#	tools/cli/cli.cpp
#	tools/completion/CMakeLists.txt
#	tools/cvector-generator/CMakeLists.txt
#	tools/cvector-generator/cvector-generator.cpp
#	tools/export-lora/CMakeLists.txt
#	tools/gguf-split/CMakeLists.txt
#	tools/gguf-split/gguf-split.cpp
#	tools/imatrix/CMakeLists.txt
#	tools/llama-bench/CMakeLists.txt
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/perplexity/CMakeLists.txt
#	tools/quantize/CMakeLists.txt
#	tools/quantize/quantize.cpp
#	tools/results/CMakeLists.txt
#	tools/server/CMakeLists.txt
#	tools/tokenize/CMakeLists.txt
#	tools/tts/CMakeLists.txt
 2026-04-17 22:37:37 +08:00
Concedo
768527b031 Merge commit '1e796eb41f' into concedo_experimental 
# Conflicts:
#	.devops/nix/package.nix
#	.github/workflows/build-riscv.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build.yml
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/development/HOWTO-add-model.md
#	embd_res/templates/Reka-Edge.jinja
#	ggml/CMakeLists.txt
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_id.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_subgroup_matrix.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	tests/test-chat.cpp
#	tools/rpc/README.md
 2026-04-17 21:47:29 +08:00
Yuri Khrustalev
a279d0f0f4
ci : add android arm64 build and release (#21647)
Some checks failed
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Details
Python check requirements.txt / check-requirements (push) Has been cancelled
Details
Python Type-Check / python type-check (push) Has been cancelled
Details
Update Operations Documentation / update-ops-docs (push) Has been cancelled
Details 
* server: respect the ignore eos flag

* ci: add android arm64 build and release

* patch

* pin android-setup actions to v4

* Apply suggestions from code review

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

* lf in the suggestion

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-04-17 11:32:24 +02:00
65a
268d61e178
mtmd: add missing struct tag (#22023) 2026-04-17 10:48:33 +02:00
Georgi Gerganov
6990e2f1f7
libs : rename libcommon -> libllama-common (#21936) 
* cmake : allow libcommon to be shared

* cmake : rename libcommon to libllama-common

* cont : set -fPIC for httplib

* cont : export all symbols

* cont : fix build_info exports

* libs : add libllama-common-base

* log : add common_log_get_verbosity_thold()
 2026-04-17 11:11:46 +03:00
Xuan-Son Nguyen
408225bb1a
server: use random media marker (#21962) 
* server: use random media marker

* nits

* remove legacy <__image__> token

* revert special char in random
 2026-04-15 23:52:22 +02:00
Concedo
ac29e6f0c0 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/vulkan.Dockerfile
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	.github/workflows/server-self-hosted.yml
#	docs/build.md
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	tests/test-backend-ops.cpp
#	tests/test-mtmd-c-api.c
 2026-04-15 15:15:19 +08:00
Xuan-Son Nguyen
707c0b7a6e
mtmd: add mtmd_image_tokens_get_decoder_pos() API (#21851) 
* mtmd: add mtmd_image_tokens_get_decoder_pos() API

* consistent naming

* fix build
 2026-04-14 16:07:41 +02:00
Concedo
236ae27329 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/close-issue.yml
#	docs/multimodal.md
#	embd_res/templates/deepseek-ai-DeepSeek-V3.2.jinja
#	ggml/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_subgroup_matrix.wgsl
#	tests/peg-parser/test-gbnf-generation.cpp
#	tests/test-chat.cpp
 2026-04-14 21:01:41 +08:00
Concedo
9c0b9b0bb1 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	docs/development/HOWTO-add-model.md
#	docs/multimodal.md
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/gated_delta_net.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/upscale.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/mtmd/CMakeLists.txt
 2026-04-14 20:06:04 +08:00
Xuan-Son Nguyen
e974923698
docs: listing qwen3-asr and qwen3-omni as supported (#21857) 
* docs: listing qwen3-asr and qwen3-omni as supported

* nits
 2026-04-13 22:28:17 +02:00
Xuan-Son Nguyen
920b3e78cb
mtmd: use causal attn for gemma 4 audio (#21824) 2026-04-13 09:47:55 +02:00
Sergiu
82764d8f40
mtmd: fix crash when sending image under 2x2 pixels (#21711) 2026-04-12 23:59:21 +02:00
Xuan-Son Nguyen
21a4933042
mtmd: qwen3 audio support (qwen3-omni and qwen3-asr) (#19441) 
* add qwen3a

* wip

* vision ok

* no more deepstack for audio

* convert ASR model ok

* qwen3 asr working

* Apply suggestions from code review

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

* nits

* Apply suggestions from code review

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

* fix bad merge

* fix multi inheritance

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-04-12 23:57:25 +02:00
Xuan-Son Nguyen
aa4695c5e5
mtmd: add gemma 4 test (vision + audio) [no ci] (#21806) 
* mtmd: add gemma 4 test (vision + audio)

* add to docs
 2026-04-12 16:29:03 +02:00
Stephen Cox
547765a93e
mtmd: add Gemma 4 audio conformer encoder support (#21421) 
* mtmd: add Gemma 4 audio conformer encoder support

Add audio processing for Gemma 4 E2B/E4B via a USM-style Conformer.

Architecture:
- 12-layer Conformer: FFN → Self-Attention → Causal Conv1D → FFN → Norm
- Subsampling Conv Projection: 2x Conv2D(stride=2) with LayerNorm
- Full self-attention with sinusoidal RPE and sliding window mask (24)
- Logit softcapping at 50.0, ClippableLinear clamping
- Output: 1024 → 1536 → RMSNorm → multimodal embedder

Mel preprocessing (dedicated mtmd_audio_preprocessor_gemma4a):
- HTK mel scale, 128 bins, magnitude STFT, mel_floor=1e-3
- Standard periodic Hann window (320 samples), zero-padded to FFT size
- Semicausal left-padding (frame_length/2 samples)
- Frame count matched to PyTorch (unfold formula)
- No pre-emphasis, no Whisper-style normalization
- Mel cosine similarity vs PyTorch: 0.9998

Key fixes:
- Tensor loading dedup: prevent get_tensor() from creating duplicate
  entries in ctx_data. Fixed with std::set guard.
- ClippableLinear clamp_info loading moved after per-layer tensors.
- Sliding window mask (24 positions) matching PyTorch context_size.
- Skip Whisper normalization for Gemma4 mel output.

Tested on E2B and E4B with CPU and Vulkan backends.
Transcribes: "Glad to see things are going well and business is starting
to pick up" (matching ground truth).

Ref: #21325
 2026-04-12 14:15:26 +02:00
Concedo
5361b45fba Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	requirements/requirements-tool_bench.txt
 2026-04-12 16:22:26 +08:00
Sirui He
073bb2c20b
mtmd : add MERaLiON-2 multimodal audio support (#21756) 
* mtmd : add MERaLiON-2 multimodal audio support

Adds support for A*STAR's MERaLiON-2 audio-language model (3B and 10B)
to the multimodal framework.

Architecture:
- Whisper large-v2 encoder for audio feature extraction
- Gated MLP adaptor: ln_speech -> frame stack (x15) -> Linear+SiLU -> GLU -> out_proj
- Gemma2 3B / 27B decoder

The mmproj GGUF is generated via convert_hf_to_gguf.py --mmproj on the full
MERaLiON-2 model directory (architecture: MERaLiON2ForConditionalGeneration).
The decoder is converted separately as a standard Gemma2 model after stripping
the text_decoder. weight prefix.

New projector type: PROJECTOR_TYPE_MERALION

Supports tasks: speech transcription (EN/ZH/MS/TA), translation, spoken QA.

Model: https://huggingface.co/MERaLiON/MERaLiON-2-3B
       https://huggingface.co/MERaLiON/MERaLiON-2-10B

* simplify comments in meralion adaptor

* meralion: use format_tensor_name, ascii arrows in comments
 2026-04-11 14:15:48 +02:00
Concedo
8b90bfe094 Merge commit '4ef9301e4d' into concedo_experimental 
# Conflicts:
#	.github/labeler.yml
#	docs/multimodal.md
#	embd_res/ggml-vocab-gemma-4.gguf
#	embd_res/ggml-vocab-gemma-4.gguf.inp
#	embd_res/ggml-vocab-gemma-4.gguf.out
#	ggml/src/ggml-sycl/fattn-tile.cpp
#	ggml/src/ggml-sycl/fattn-tile.hpp
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	ggml/src/ggml-sycl/fattn.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q8_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-f16.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q4_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q4_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q5_0.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q5_1.cpp
#	ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q8_0.cpp
#	tests/CMakeLists.txt
#	tests/test-jinja.cpp
#	tools/mtmd/CMakeLists.txt
 2026-04-11 09:38:50 +08:00
Xuan-Son Nguyen
501aeed18f
mtmd: support dots.ocr (#17575) 
* convert gguf

* clip impl

* fix conversion

* wip

* corrections

* update docs

* add gguf to test script
 2026-04-09 12:16:38 +02:00
Concedo
c82c0b463a Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/release.yml
#	examples/debug/debug.cpp
#	ggml/src/ggml-cuda/common.cuh
#	ggml/src/ggml-cuda/mmq.cuh
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/mtmd/CMakeLists.txt
 2026-04-09 17:45:04 +08:00
forforever73
09343c0198
model : support step3-vl-10b (#21287) 
* feat: support step3-vl-10b

* use fused QKV && mapping tensor in tensor_mapping.py

* guard hardcoded params and drop crop metadata

* get understand_projector_stride from global config

* img_u8_resize_bilinear_to_f32 move in step3vl class

* Apply suggestions from code review

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

* fix the \r\n mess

* add width and heads to MmprojModel.set_gguf_parameters

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-04-08 09:51:31 +02:00
Concedo
15d269197e Merge commit '506200cf8b' into concedo_experimental 
# Conflicts:
#	docs/multimodal.md
#	scripts/compare-llama-bench.py
#	src/llama-vocab.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
 2026-04-07 14:58:36 +08:00