llama : fix parameter order for hybrid memory initialization (#14725)

llama : add high-throughput mode (#14363)

* kv-cache : prepare K/V buffers for separation

ggml-ci

* batched-bench : fix oob write

ggml-ci

* llama : add "virtual sequences"

ggml-ci

* llama : use "stream" vs "virtual sequence"

ggml-ci

* graph : fix stream splitting when KV cache is not used

ggml-ci

* kv-cache : add multi-stream save/load support

ggml-ci

* llama : add "--attn-streams" flag

ggml-ci

* kv-cache : fix handling when find_slot fails

ggml-ci

* kv-cache : restore find_slot impl

ggml-ci

* kv-cache : add comments

* kv-cache : add bounds checks for sequence id

ggml-ci

* cont : add n_seq_max to batch allocr

ggml-ci

* kv-cache : perform stream copies lazily after llama_synchronize

ggml-ci

* kv-cache : avoid throwing exceptions across the C boundary

ggml-ci

* CUDA: 4D FlashAttention support (#14628)

* CUDA: 4D FlashAttention support

* CUDA: fix WMMA FA kernel

* llama : rename attn_streams -> kv_unified

ggml-ci

* common : rename kv_split -> kv_unified

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

scripts: synthetic prompt mode for server-bench.py (#14695)

gguf-py : dump bpw per layer and model in markdown mode (#14703)

vulkan: add RTE variants for glu/add/sub/mul/div (#14653)

cuda: fix build warnings in set-rows.cu (unused variable) (#14687)

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

CUDA: fix FTZ in FA for Gemma 3 (#13991)

opencl: add `backend_synchronize` (#13939)

* This is not needed by the normal use where the result is read
  using `tensor_get`, but it allows perf mode of `test-backend-ops`
  to properly measure performance.

server : disable speculative decoding for SWA models (#13970)

* server : use swa-full fo draft context

ggml-ci

* server : disable speculative decoding for SWA models

cmake : Handle mixed-case 'Power' strings in POWER CPU detection (#13…