Misc. bug: infinite loop of @

[trivita]

Name and Version

ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: turbo3 using 4-mag LUT (pre-M5 hardware)
ggml_metal_library_init: turbo3 sparse V dequant enabled (opt-out: TURBO_SPARSE_V=0)
ggml_metal_library_init: loaded in 0.018 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: MTL0
ggml_metal_device_init: GPU family: MTLGPUFamilyApple8 (1008)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4 (5002)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 55662.79 MB
version: 8670 (8ad0f00)
built with AppleClang 17.0.0.17000604 for Darwin arm64

build : b8670-8ad0f00e9
model : Qwen_Qwen3.5-35B-A3B-Q4_K_M_1.gguf
modalities : text
que start_loop: processing new tasks

Operating systems

Mac

Which llama.cpp modules do you know to be affected?

llama-cli

Command line

./build/bin/llama-cli -m ~/Downloads/Persepolis/Qwen_Qwen3.5-35B-A3B-Q4_K_M_1.gguf

Problem description & steps to reproduce

the compilation was succesfull.
but no matter what model i use.
llama-cpp keeps giving me infinite loop of @ symbol.
even without using turbo3 kv

First Bad Commit

No response

Relevant log output

Logs