Vulkan Improvements (llama/5835)

fix mul_mat fault in CI/unit-test (llama/5862)

ggml : fix unknown status (llama/0)

whisper : fix compute helper return (ggml/750)

ggml : introduce ggml_status (ggml/750)

cuda : fix data race in soft max (llama/5853)

ggml : fix IQ3_S AVX implementation (llama/5834)

ggml : IQ3_S improvements (llama/5829)

Support multiple GPUs (split mode) on SYCL backend (llama/5806)

ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was previously broken (llama/5813)

Use batched mul_mat pathway (llama/5591)

make portability_enumeration_ext apple only (llama/5757)

add some new ops, fix some operators and add batch operations to certain operators. (ggml/747)

examples : Auto lowercase language parameter in main.cpp (#1928)

examples : fix typo in bench.cpp (#1933)

whisper : fix typo (#1925)

whisper.android.java : fix returns in JNI (#1929)

cmake : add library versioning (#1352)

readme : recommend MacOS Sonoma for Core ML (#1917)

talk-llama : sync llama.cpp

sync : ggml

sync : llama.cpp (ggml/0)

ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (llama/5760)

Attempt to fix android build (llama/5752)

IQ4_XS: a 4.25 bpw quantization (llama/5747)

cuda : replace remaining shfl_xor with calls to warp_reduce functions (llama/5744)

ggml-quants : fix avx2 iq1_s vec_dot when compiled with gcc (llama/5742)

Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (llama/5721)

CUDA: fix DEBUG_CUDA_MALLOC (llama/5729)

Add support for soft_max ALiBi (llama/5639)

ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (llama/5711)

add google magika inference example (ggml/748)

stream.wasm : fix invalid memory access when no segments (#1902)

talk-llama : sync llama.cpp

sync : ggml

sync : llama.cpp (ggml/0)

code : normalize enum names (llama/5697)

IQ3_S: a much better alternative to Q3_K (llama/5676)

Introduce backend GUIDs (ggml/743)

talk, talk-llama : pass text_to_speak as a file (#1865)

whisper : add SYCL support (#1863)

talk-llama : sync llama.cpp

sync : ggml

ggml : always define ggml_fp16_t as uint16_t (llama/5666)

ci : fix whitespace

ggml : 32-bit arm compat (#1891)

sync : ggml

sync : llama.cpp (ggml/0)

conext add name (llama/5624)

Update ggml_sycl_op_mul_mat_vec_q (llama/5502)