Issue ggml_vulkan: device Vulkan0 does not support 16-bit storage.

[codingWiz-rick]

Hii,
I'm getting an error while using whisper.cpp with vulkan here is the error while trying to use with Adreno (TM) 610

whisper_init_from_file_with_params_no_state: loading model from '/data/data/com.codewiz.ailyrics/files/home/whisper.cpp/models/ggml-tiny.bin' whisper_init_with_params_no_state: use gpu = 1 whisper_init_with_params_no_state: flash attn = 0 whisper_init_with_params_no_state: gpu_device = 0 whisper_init_with_params_no_state: dtw = 0 ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Adreno (TM) 610 (Qualcomm Technologies Inc. Adreno Vulkan Driver) | uma: 1 | fp16: 0 | warp size: 64 | shared memory: 16384 | int dot: 0 | matrix cores: none whisper_init_with_params_no_state: devices = 2 whisper_init_with_params_no_state: backends = 2 whisper_model_load: loading model whisper_model_load: n_vocab = 51865 whisper_model_load: n_audio_ctx = 1500 whisper_model_load: n_audio_state = 384 whisper_model_load: n_audio_head = 6 whisper_model_load: n_audio_layer = 4 whisper_model_load: n_text_ctx = 448 whisper_model_load: n_text_state = 384 whisper_model_load: n_text_head = 6 whisper_model_load: n_text_layer = 4 whisper_model_load: n_mels = 80 whisper_model_load: ftype = 1 whisper_model_load: qntvr = 0 whisper_model_load: type = 1 (tiny) whisper_model_load: adding 1608 extra tokens whisper_model_load: n_langs = 99 ggml_vulkan: device Vulkan0 does not support 16-bit storage. libc++abi: terminating due to uncaught exception of type std::runtime_error: Unsupported device

Can you please tell me how to solve this error

[geobra]

I have the same issue on a OnePlus 6, running PostmarketOS.

Activated Vulkan support during build time by cmake.

This is the output on my device:

oneplus-enchilada:~/Documents/whisper.cpp$ time ./build/bin/whisper-cli -m ./models/ggml-base.en.bi
n -f ~/.local/share/org.gnome.SoundRecorder/Recording3.vob -t 8
whisper_init_from_file_with_params_no_state: loading model from './models/ggml-base.en.bin'
whisper_init_with_params_no_state: use gpu    = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw        = 0
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Turnip Adreno (TM) 630 (turnip Mesa driver) | uma: 1 | fp16: 0 | warp size: 128 | shared memory: 32768 | int dot: 0 | matrix cores: none
whisper_init_with_params_no_state: devices    = 2
whisper_init_with_params_no_state: backends   = 2
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51864
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 512
whisper_model_load: n_audio_head  = 8
whisper_model_load: n_audio_layer = 6
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 512
whisper_model_load: n_text_head   = 8
whisper_model_load: n_text_layer  = 6
whisper_model_load: n_mels        = 80
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 2 (base)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: n_langs       = 99
ggml_vulkan: device Vulkan0 does not support 16-bit storage.
terminate called after throwing an instance of 'std::runtime_error'
  what():  Unsupported device
Command terminated by signal 6

It is running fine (but slow) with only CPU support.

I am happy to test and try out some code changes if someone points me in the right direction.