vendor : update LibreSSL to 4.3.1 (#22285)

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

fix build number for sycl release (#22283)

server: Enable transcriptions API for LFM2-Audio (#22000)

metal : fix event synchronization (#22260)

HIP: flip GGML_HIP_GRAPHS to default on (#22254)

In #11362 hip graph was disabled by default as, at the time, its performance impact was negative. Due to improvements in rocm and our usage and construction of graphs this is no longer true, so lets change the default.

[WebGPU] Implement async tensor api and event api (#22099)

• Only run webgpu CI on my fork

• Implement set_tensor_async

• Implement synchronize api

• Implement event creation and deletion API

• Cleanup

• Cleanup

• Comment out jobs for local CI run

• Add webgpu only workflow

• Delete .github/workflows/build-webgpu.yml

• Cleanup

• Cleanup

• Update API with function handlers

• Run clang-format

• Replace one-shot buffer with a direct queue.WriteBuffer using the buffer context

ggml-webgpu: Add fused RMS_NORM + MUL (#21983)

• fused rms_norm_mul + mul

• Add GGML_WEBGPU_DISABLE_FUSION for being able to disable kernel fusion.

• Decouple num_fused_ops from webgpu_context; misc cleanup

• Fix eps handling and remove disable_fusion.

• Fix not to use c++20 initializers.

chat: fix parallel_tool_calls default setting based on model capabilities, add tests for parallel tool calls and structured outputs (#22217)

• chat: fix parallel_tool_calls default setting based on model capabilities, add tests for parallel tool calls and structured outputs

• Fix ty errors.

• Fix flake8 err

speculative-simple : add checkpoint support (#22227)

• speculative-simple : add checkpoint support

• cont : fix build

sycl: Improve mul_mat_id memory efficiency and add BF16 fast path (#22119)

• sycl: size mul_mat_id staging buffers by routed rows

Previously src1_contiguous/dst_contiguous in ggml_sycl_mul_mat_id were
sized to ggml_nelements(src1/dst), which over-allocates when ne12 > 1
and can fail with UR_RESULT_ERROR_OUT_OF_HOST_MEMORY on Level Zero for
MoE models (notably with --cpu-moe). Size them by the actual number of
routed rows (ids->ne[1] * n_ids) instead.

• sycl: add bf16 mul_mat fast path via DNNL

When src0 is BF16 (commonly the case for lm_head / output.weight), the
existing f16 path is skipped because bf16 isn't covered, and the f32
fallback dequantizes the entire src0 slab to f32 in a single pool alloc
(row_diff*ne00 floats). For large-vocab models this can reach several
GB and fail with UR_RESULT_ERROR_OUT_OF_HOST_MEMORY on Level Zero.

Add a bf16xbf16 -> f32 DNNL matmul fast path that uses the bf16 storage
in place and only materializes a small src1 bf16 conversion buffer. bf16
matmul accumulates in f32, so it's correct even when the op requests
GGML_PREC_F32 (as lm_head does).

• gemm.hpp: map bfloat16 to dnnl::memory::data_type::bf16.
• convert.{hpp,cpp}: expose ggml_get_to_bf16_sycl for f32/f16/bf16 -> bf16.
• ggml-sycl.cpp: take the bf16 path early in ggml_sycl_op_mul_mat_sycl
  when DNNL and GGML_SYCL_HAS_BF16 are both available.