Signed-off-by: xiaofei <[email protected]>

* docker : do not build tests

* include "ggml-cpu.h"

* arg : allow using -hf offline

* add more comments in code [no ci]

z17 compilation requires GCC 15.1.0 and onwards

Signed-off-by: Aaron Teo <[email protected]>

Build fails with compilation error on power pc.
This patch fixes the same.

Tested with unit tests run via
 --build <build_dir> && cd <build_dir> && make test

Signed-off-by: Shalini Salomi Bodapati <[email protected]>

* convert : improve model arch handling

* use AutoConfig

* rm trust_remote_code

* Update convert_hf_to_gguf.py

* fix self.block_count for vision

* fix NomicBertModel

* arg : -hf do not fail if url mismatch

* do not return if cannot parse metadata json

ggml-ci

…ggml-org#13223)

* convert ok

* load ok, missing patch merger

* ah sheet it works

* update llava/readme

* add test

* fix test

* whisper: suppress Windows compiler warnings

This commit disables compiler warnings on window using MSVC.

The motivation for these changes is that some compilers generate
warnings for these conversion, for example Windows MSVC, and
there are quite a few of them. This makes it a little difficult to
spot new warnings that may be introduced and also can be difficult
for users/embedders of ggml where these warnings are hard to separate
from their own warnings.

* squash! whisper: suppress Windows compiler warnings

Move ggml related warnings into ggml. This commit also fixes the
indentation and adds a missing whitespace to the if statement.

This commit adds a check to makes sure that the target exists before
trying to add compile options to ignore warnings when using MSVC.

The motivation for this is currently the build is broken depending on
the cmake options provided. With this fix it should be possible to build
even if the targets are not actually available.

Refs: ggml-org/whisper.cpp#3090 (comment)

ggml-ci

…der (ggml-org#13191)

* vulkan: Handle src1 batch dimension in non-contiguous mat-vec-mul shader

* vulkan: Add bfloat16 support

This adds bfloat16 matrix multiply support based on VK_KHR_shader_bfloat16.
The extension is required for coopmat multiply support, but matrix-vector
multiply trivially promotes bf16 to fp32 and doesn't require the extension.
The copy/get_rows shaders also don't require the extension.

It's probably possible to fall back to non-coopmat and promote to fp32 when
the extension isn't supported, but this change doesn't do that.

The coopmat support also requires a glslc that supports the extension, which
currently requires a custom build.

* vulkan: Support bf16 tensors without the bf16 extension or coopmat support

Compile a variant of the scalar mul_mm shader that will promote the bf16
values to float, and use that when either the bf16 extension or the coopmat
extensions aren't available.

* vulkan: bfloat16 fixes (really works without bfloat16 support now)

* vulkan: fix spirv-val failure and reenable -O

* update GLM4 chat template

* Update chat template

Co-authored-by: Xuan-Son Nguyen <[email protected]>

---------

Co-authored-by: Xuan-Son Nguyen <[email protected]>

… image size (ggml-org#13237)

* build : fix build info on windows

* fix cuda host compiler msg

The following scenario will cause an assertion failure in the graph
allocator:
 - Build and allocate a graph containing a tensor with a non-NULL data
   pointer
 - Build and allocate a new graph where that data is NULL

Result:
ggml-alloc.c:819: GGML_ASSERT(talloc->buffer_id >= 0) failed

This happens during revalidation because we think that memory should
have been previously allocated based on the current graph but in
reality the previous graph was different. In this situation, we
should do a full reallocation pass.

ggml-ci

…#12858)

* sycl : Implemented reorder Q4_0 mmvq

Signed-off-by: Alberto Cabrera <[email protected]>

* sycl : Fixed mmvq being called when reorder is disabled

* sycl : Improved comments in the quants header

Signed-off-by: Alberto Cabrera <[email protected]>

* Use static_assert

* safe_div -> ceil_div

* Clarify qi comment

* change the reorder tensor from init to execute OP

* dbg

* Undo changes to test-backend-ops

* Refactor changes on top of q4_0 reorder fix

* Missing Reverts

* Refactored opt_for_reorder logic to simplify code path

* Explicit inlining and unroll

* Renamed mul_mat_algo enum for consistency

---------

Signed-off-by: Alberto Cabrera <[email protected]>
Co-authored-by: romain.biessy <[email protected]>

* server : (experimental) vision support via libmtmd

* mtmd : add more api around mtmd_image_tokens

* mtmd : add more api around mtmd_image_tokens

* mtmd : ability to calc image hash

* shared_ptr for mtmd_image_tokens

* move hash to user-define ID (fixed)

* abstract out the batch management

* small fix

* refactor logic adding tokens to batch

* implement hashing image

* use FNV hash, now hash bitmap instead of file data

* allow decoding image embedding to be split into batches

* rm whitespace

* disable some features when mtmd is on

* fix --no-mmproj-offload

* mtmd_context_params no timings

* refactor server_inp to server_tokens

* fix the failing test case

* init

* wip

* working version

* add mtmd::bitmaps

* add test target

* rm redundant define

* test: mtmd_input_chunks_free

* rm outdated comment

* fix merging issue

* explicitly create mtmd::input_chunks

* mtmd_input_chunk_copy

* add clone()

* improve server_input struct

* clip :  fix confused naming ffn_up and ffn_down

* rm ffn_i/o/g naming

* rename n_embd, n_ff

* small fix

* no check n_ff

* fix detokenize

* add const to various places

* add warning about breaking changes

* add c api

* helper: use mtmd_image_tokens_get_n_pos

* fix ctx_shift

* fix name shadowing

* more strict condition

* support remote image_url

* remote image_url log

* add CI test

* do not log base64

* add "has_multimodal" to /props

* remove dangling image

* speculative: use slot.cache_tokens.insert

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <[email protected]>

* rm can_be_detokenized

* on prmpt processing done, assert cache_tokens.size

* handle_completions_impl returns void

* adapt the new web ui

* update docs and hot topics

* rm assert

* small fix (2)

---------

Co-authored-by: Georgi Gerganov <[email protected]>

…gml-org#13413)

* vulkan: scalar flash attention implementation

* vulkan: always use fp32 for scalar flash attention

* vulkan: use vector loads in scalar flash attention shader

* vulkan: remove PV matrix, helps with register usage

* vulkan: reduce register usage in scalar FA, but perf may be slightly worse

* vulkan: load each Q value once. optimize O reduction. more tuning

* vulkan: support q4_0/q8_0 KV in scalar FA

* CI: increase timeout to accommodate newly-supported tests

* vulkan: for scalar FA, select between 1 and 8 rows

* vulkan: avoid using Float16 capability in scalar FA

* arg : add env var to control mmproj

* small note about -hf --mmproj

* convert : internvl support

* InternVL3-1B working

* fix regression

* rm mobilevlm from test

* fix conversion

* add test for internvl

* add to list of pre-quant

* restore boi/eoi check

* add clarify comment for norm eps

before cleanup: 20G
after cleanup: 44G
after all built and pushed: 24G

https://github.com/Thammachart/llama.cpp/actions/runs/14945093573/job/41987371245

…ml-org#13434)

* mtmd : add hard limit on image resolution for qwen2vl / qwen2.5vl

* fix typo

* mtmd : move helpers to dedicated file

* fix windows build

* rm redundant include

* Support InternVL 3 38B and 78B mmproj

* Swap norms in clip.cpp

* Group variables together

…ma4 400B (ggml-org#13386)

… to compare (ggml-org#13451)

* add constructor to initialize server_context::batch, preventing destructor's call to llama_batch_free from causing an invalid free()

* Update tools/server/server.cpp

Co-authored-by: Xuan-Son Nguyen <[email protected]>

* use C++11 initializer syntax

* switch from Copy-list-initialization to Direct-list-initialization

---------

Co-authored-by: Xuan-Son Nguyen <[email protected]>