metal: fix memory unwire if model is freed without any GPU operations (#26082)

• metal: fix memory leak if model is freed without any GPU operations

• metal: run dummy work only if residency sets are used

• metal: wrap function in #if defined

• metal: measure system-wide wired memory in test

• metal: always build regression test

Co-authored-by: YiChen Lv 63285796+forforever73@users.noreply.github.com

Co-authored-by: YiChen Lv 63285796+forforever73@users.noreply.github.com

ggml : Fix issue with kleidiai ci and stringop overflow warning (#26277)

Signed-off-by: Jonathan Clohessy Jonathan.Clohessy@arm.com

mimo2: address MTP review feedback (#26228)

Co-authored-by: tnhnyc 115956684+tnhnyc@users.noreply.github.com

llama: move suppress_tokens handling to common/sampling (#26276)

• llama: move suppress_tokens handling to common/sampling

• address security issues

• rm has_logit_bias

ggml-cuda : disable MMQ on devices with less than 48 KiB shared memory (#26141)

ggml_cuda_should_use_mmq() selects MMQ purely from the quantization
type. The current MMQ configurations are designed and maintained against
a minimum of 48 KiB per-block shared memory, the limit provided by
NVIDIA Pascal GPUs and later. On devices that report less, no supported
MMQ tile fits and mul_mat_q_switch_J() aborts when every tile size
exceeds the device's per-block shared memory budget.

Disable MMQ when smpbo < 48 KiB so the caller falls back to the BLAS
path instead of hitting GGML_ABORT. Some current MUSA QY1 devices
report only 28 KiB and are covered by this guard.

Reproduced on a Moore Threads MTT S70 (arch mp_21, 28 KiB shared memory
per block) with an RWKV-7 0.1B Q8_0 model:

$ llama-bench -m rwkv7-g1d-0.1b-Q8_0.gguf -p 128 -n 0
J_best=0
ggml/src/ggml-cuda/template-instances/../mmq.cuh:1521: fatal error
(core dumped)

Only prefill (batch > 1) is affected; token generation is fine. After
the fix the same device falls back to the BLAS path:

Q8_0 pp128 1470.7 t/s, tg8 55.3 t/s (was: abort)
FP16 unchanged
Q4_K_M unchanged

This matches a -DGGML_CUDA_FORCE_CUBLAS=ON build (pp128 1464.2 t/s),
which confirms the fallback path is the one being taken.

This is not MUSA-specific: any device with less than 48 KiB per-block
shared memory is affected.

Co-authored-by: KakaruHayate KakaruHayate@users.noreply.github.com

sycl: contiguous fast path + 32-bit index math for unary elementwise ops (#25946)

• sycl: contiguous fast path + 32-bit index math for unary elementwise ops

• sycl: use fastdiv for elementwise index math

vendor: update BoringSSL to 0.20260728.0 (#26241)

server : add trace logging for slot similarity checking (#26271)

Adds trace logging in server-context.cpp for slot similarity checking
during prompt cache slot selection, including skip reasons and similarity
calculation details.

Assisted-by: llama.cpp:Qwen3.6-27B

RPC: add tensor_memset (#25912)

add rdna3.5, and 3 to mmq configs so they can be tuned independently. (#26199)