ggml : group all experts in a single ggml_mul_mat_id (llama/6505)

fix mul_mat_id() for new input, make the ut pass (llama/6682)

fix memcpy() crash, add missed cmd in guide, fix softmax (llama/6622)

remove row=1 cond (llama/6532)

support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (llama/6521)

Fixed minor bug when enabling FP16 for non intel targets (llama/6464)

Disable iqx on windows as WA (llama/6435)

fix set main gpu crash (llama/6339)

sync : ggml (#2001)

llama : add pipeline parallelism support (llama/6017)

Update get version (llama/6025)

ggml : reuse quantum structs across backends (llama/5943)

sycl : update IQ1_S kernels (WIP - not working!) (llama/5995)

Add q3_s and q1_s (llama/5886)

ggml : add ggml-common.h to deduplicate shared code (llama/5940)

Revert "[SYCL] fix error when set main gpu to non-zero (llama/5901)" (llama/5918)

fix error when set main gpu to non-zero (llama/5901)

add wait() to make code stable (llama/5895)

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

ggml : introduce ggml_status (ggml/750)

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

Use batched mul_mat pathway (llama/5591)

Add support for soft_max ALiBi (llama/5639)

code : normalize enum names (llama/5697)

Introduce backend GUIDs (ggml/743)

conext add name (llama/5624)

Update ggml_sycl_op_mul_mat_vec_q (llama/5502)

ggml-sycl: Replace 3d ops with macro (llama/5458)

src : relocate new backend sources