llama : offload to RPC in addition to other backends (llama/7640)

ggml : use OpenMP as a thread pool (llama/7606)

Vulkan Mixture of Experts (MoE) support (llama/7628)

kompute : implement op_getrows_f32 (llama/6403)

fix bug introduced in using calloc (llama/7701)

Fix FlashAttention debug test, FP32 assert (llama/7684)

CUDA: fix Pascal FA, deq. KV to FP16 for batch > 8 (llama/7681)

CUDA: quantized KV support for FA vec (llama/7527)

ggml : fix loongson compile warnings (llama/7537)

faster avx512 exp implementation (llama/7551)

ggml : fix loongarch build (O2 issue) (llama/7636)

metal : remove invalid asserts (llama/7617)

metal : add missing asserts (llama/7617)

ggml : fix YARN + add tests + add asserts (llama/7617)

cuda : non-cont concat support (llama/7610)

llama-bench : add support for the RPC backend (llama/7435)

ggml : use atomic_flag for critical section (llama/7598)

examples : adapt to new ggml_concat (ggml/0)

ggml : fix typo in ggml.c (llama/7603)

Align GEMM dispatch (llama/7566)

sycl : fix assert (llama/7563)

vulkan: properly initialize vulkan devices for LLAMA_SPLIT_MODE_NONE (llama/7552)

rpc : resource management rework (llama/7562)

fix ggml_sycl_mul_mat_id() to match the change of api (llama/7436)

ggml : generalize GGML_OP_CONCAT (llama/7563)

update HIP_UMA #7399 (llama/7414)

Allow multiple copy function pointers for CUDA graph kernel param updates (llama/7565)

Fix q_xxs using mul_mat_q (llama/7459)

Add freq factors (llama/7495)

metal : add GGML_OP_REPEAT kernels (llama/7557)

metal : disable FA kernel for HS=256 (llama/7556)

ggml : restore ggml_rope_xpos_inplace (ggml/0)

ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (llama/7433)

ggml : silence UB sanitizer error during iq2_xxs quantization (llama/0)

ggml : remove ggml_flash_attn and ggml_flash_ff (llama/7463)

ggml : drop support for QK_K=64 (llama/7473)

Update vulkan rope implementation to support frequency factors (llama/7475)

CUDA: fix FA out-of-bounds reads (llama/7479)

CUDA: fix FA out-of-bounds writes (llama/7465)

cuda : fix compile warning (llama/7454)

CUDA: remove incorrect precision check (llama/7454)

cuda : fix rope + add tests (llama/7452)

llama : add phi3 128K model support (llama/7225)

metal : handle F16 inf values, fix FA partial offload (llama/7434)

CUDA: fix unused warning in mmq.cu (llama/7442)

CUDA: deduplicate mmq code (llama/7397)

rpc : track allocated buffers (llama/7411)

Update SYCL upscale operation (llama/7321)

ggml-opencl, llama: using reserve() if count already known (llama/7272)

ggml : add loongarch lsx and lasx support (llama/6454)