ggml: initial IBM zDNN backend (llama/14975)

finetune: SGD optimizer, more CLI args (llama/13873)

ggml : update `ggml_rope_multi` (llama/12665)

llama : add gpt-oss (llama/15091)

ggml : remove old kompute, cann (skip) (#3349)

ggml: Add initial WebGPU backend (llama/14521)

sync : resolve conflicts (ggml/0)

ggml : add ggml_scale_bias (llama/14417)

CUDA: add bilinear interpolation for upscale (llama/14563)

ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445)

ggml : fix FA mask dim 2 and 3 (llama/14505)

llama : initial Mamba-2 support (llama/9126)

ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (llama/14435)

ggml : Callback before abort (llama/14481)

ggml : add version function to get lib version (ggml/1286)

Add Conv2d for CPU (llama/14388)

ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158)

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366)

ggml : add ggml_set_rows (llama/14274)

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317)

ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)

Add `ggml_roll` (ggml/1274)

threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995)

ggml : add ggml_repeat_4d (llama/13824)

ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247)

ggml : fix the order of ggml_unary_op (llama/13718)

ggml : add ggml_gelu_erf() (llama/13667)

mnist: fix segmentation fault (ggml/1227)

llama/ggml: add LLM training support (llama/10544)

Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama/13386)

CUDA: fix bad asserts for partial offload (llama/13337)

CUDA: fix logic for clearing padding with -ngl 0 (llama/13320)

CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (llama/13137)

ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (llama/13107)

rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (llama/12943)

ggml : fix ggml_gallocr_ptr type (ggml/1205)

rpc : add RPC_CMD_HELLO (llama/12955)

ggml : Depthwise 2D convolution (ggml/1152)

ggml : add bilinear upscale support (ggml/1185)

ggml : add more generic custom op, remove deprecated custom ops (ggml/1183)

metal : improve FA + improve MoE (llama/12612)

rpc : send hash when tensor data is above some fixed threshold (llama/12496)

llama: Add support for RWKV v7 architecture (llama/12412)

ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)

ggml : portability fixes for VS 2017 (llama/12150)

ggml : upgrade init_tensor API to return a ggml_status (llama/11854)

ggml-cpu: Support s390x SIMD Instruction Set (llama/12019)

ggml-cpu: Add CPU backend support for KleidiAI library (llama/11390)

repo : update links to new url (llama/11886)

cleanup: fix compile warnings associated with gnu_printf (llama/11811)