* cmake : enable curl by default

* no curl if no examples

* fix build

* fix build-linux-cross

* add windows-setup-curl

* fix

* shell

* fix path

* fix windows-latest-cmake*

* run: include_directories

* LLAMA_RUN_EXTRA_LIBS

* sycl: no llama_curl

* no test-arg-parser on windows

* clarification

* try riscv64 / arm64

* windows: include libcurl inside release binary

* add msg

* fix mac / ios / android build

* will this fix xcode?

* try clearing the cache

* add bunch of licenses

* revert clear cache

* fix xcode

* fix xcode (2)

* fix typo

…et_tensor (ggml-org#12734)

… (ggml/1167)

* cpu: refactor SIMD mappings and vectorized op functions into separate files

* Fix warning for ggml_float to float

* Fix warnings

* cpu: move all the operations (except mul_mat) to a separate c++ file

* fix whitespace

* Update ggml/src/ggml-cpu/vec.h

Co-authored-by: Diego Devesa <[email protected]>

* Fix PR comments - use GGML_UNUSED, use cassert in ops.cpp

* Reverse the order of import for ops.h and vec.h, to match what was present in ggml-cpu.c previously

---------

Co-authored-by: Diego Devesa <[email protected]>

* add bf16 support

* use convert_from_bf16_cuda instead of convert_unary_cuda for f32

* revert 7ec5085

* move functionality into convert_unary with constexpr

* ggml : simlpify Arm fp16 CPU logic

ggml-ci

* cont : bring back CUDA/MUSA checks

ggml-ci

ggml-ci

ggml-ci

* llama4 conversion

* initial support, no chat template

* clean up a bit

* fix tokenizer conversion

* correct hparams

* try this

* fix shexp

* ffn_inp_normed

* chat template

* clean up model conversion

* add_bos

* add scale_before_ffn

* fix order

* weight_before_ffn

* llm_graph_input_attn_temp

* add chunk attn mask

* build_inp_attn_scale()

* add comment about ggml_repeat

* clarify comments

* fix build

* gguf-py : support lazy tensor splitting

Splitting usually involves returning tuples of tensors,
which need to be handled properly to avoid early eager evaluation.

* gguf-py : fix flake8 lint

…uffer_set_tensor" (ggml-org#12812)

* Revert "sycl: remove redundant memcopy in function ggml_backend_sycl_buffer_s…"

This reverts commit 518a014.

* Update ggml/src/ggml-sycl/ggml-sycl.cpp

* Update ggml/src/ggml-sycl/ggml-sycl.cpp

* rm tail space

…rg#12785)

* Update ChatScreen.tsx

* useAutosizeTextarea.ts

useAutosizeTextarea to encapsulate the logic.

* Implement responsive auto-sizing chat textarea

Replaces the manual textarea resizing with an automatic height adjustment based on content.

- `useChatTextarea` hook to manage textarea state and auto-sizing logic via refs, preserving the optimization
- Textarea now grows vertically up to a maximum height (`lg:max-h-48`) on large screens (lg breakpoint and up).
- Disables auto-sizing and enables manual vertical resizing (`resize-vertical`) on smaller screens for better mobile usability.
- Aligns the "Send" button to the bottom of the textarea (`items-end`) for consistent positioning during resize.

* -update compressed index.html.gz after npm run build
-refactor: replace OptimizedTextareaValue with AutosizeTextareaApi in VSCode context hook

* chore: normalize line endings to LF
refactor: AutosizeTextareaApi -> chatTextareaApi

* refactor: Rename interface to PascalCase

---------

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

…text (ggml-org#12824)

Signed-off-by: dm4 <[email protected]>

…12825)

* ggml : FA supports F32 V

* graph : cast KV to F16 when the KV cache is not used

ggml-ci

* server : add test that exercises embeddings with FA enabled

ggml-ci

…ml-org#12834)

This allows BF16 KV-cache on CUDA.

…#12783)

This is consistent with the ggml-cuda behavior and the mul_mat fallback.

…gml-org#12833)

q4_k and q5_k had a lot of redundant global loads where the same 16B of
scale information is repeatedly loaded and decoded during each loop iteration.
This change restructures the loops to more explicitly iterate over whole
blocks in the outer loop (with unrolled inner loop) and to copy/decode the
scale data into shared memory once at the start of each outer loop. The copy
is pipelined so the scale load from global memory is relatively cheap.

This improves q4_k/q5_k model prompt processing performance by around 5-7%.
I briefly tried applying this to q6_k and q4_0, and it didn't help for q6_k
and hurt for q4_0.

The big "else" path in mul_mm_cm2.comp that had all the clamped/unclamped
variants isn't used as often as it originally was (e.g. due to the padded_N
change), so I trimmed it down to offset some of the new complexity of the
semi-manual loop unrolling.

* [CANN] Support ELU and CONV_TRANSPOSE_1D

* [CANN]Modification review comments

* [CANN]Modification review comments

* [CANN]name adjustment

* [CANN]remove lambda used in template

* [CANN]Use std::func instead of template

* [CANN]Modify the code according to the review comments

---------

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

* fix: detach common from the library

* fix: building chat test template

Signed-off-by: Xiaodong Ye <[email protected]>

* add qwen3 & qwen3moe support.

* fix

---------

Co-authored-by: bozheng-hit <[email protected]>

Submit operators using asynchronous threads to improve performance.

Use the environment variable GGML_CANN_ASYNC_MODE to control whether
asynchronous submission is enabled. It is disabled by default.

Testing shows a 10%–20% performance improvement in scenarios with
small parameter sizes, especially in quantized models.

…rg#12970)

…-org#12953)

* graph : make mla compatible with FA

* metal : add exp FA kernels for DeepSeek models

ggml-ci

* llama : minor naming updates

ggml-ci

* ggml : disable FA for DS head sizes

* tests : add FA tests for MLA shapes

ggml-ci

Add RPC_CMD_HELLO for getting the version of the protocol implemend by
the server. Follow the semantic versioning rules at https://semver.org

Hopefully this bring better user experience when we make breaking
changes at the protocol level and avoid issues like ggml-org#12465

* 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)

* fix prompt_modified

* rm redundant data member

* SYCL: refactor move to a separate file

* Fix binbcast

* Remove duplicates

* fix include formatting

* fix typo

* server : use std::move whenever possible

* use r-value ref

* Apply suggestions from code review

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

* make task creation scoped

* restore std::move

* fix task_id not set correctly

* apply changes from suggestion

Co-authored-by: ggerganov <[email protected]>

---------

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

This restores the behavior from ggml-org#491. This does not affect Ctrl+D's ability to
terminate --multiline-input lines (ggml-org#1040).

This also actually implements ggml-org#587: "If the user wants the text to end in a
newline, this should be accomplished by explicitly adding a newline by using
\ followed by return, then returning control by pressing return again."

Fixes ggml-org#12949

…ml-org#13011)

* clip : refactor, add `image_manipulation` and `llava_uhd`

* refactor llava-1.6 preprocessing

* simplify logic for llava-1.5

* missing include