whisper.cpp

whisper.cpp copied to clipboard

GGML_SYCL_DEVICE=0 ./build/bin/main -m models/ggml-base.bin -f samples/jfk.wav
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-base.bin'
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51865
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 1608 extra tokens
whisper_model_load: n_langs       = 99
whisper_backend_init: using SYCL backend
[SYCL] call ggml_init_sycl
ggml_init_sycl: GGML_SYCL_DEBUG: 1
ggml_init_sycl: GGML_SYCL_F16: yes
[SYCL] call ggml_backend_sycl_print_sycl_devices
found 4 SYCL devices:
|  |                  |                                             |Compute   |Max compute|Max work|Max sub|               |
|ID|       Device Type|                                         Name|capability|units      |group   |group  |Global mem size|
|--|------------------|---------------------------------------------|----------|-----------|--------|-------|---------------|
| 0|[level_zero:gpu:0]|                 Intel(R) Iris(R) Xe Graphics|       1.3|         80|     512|     32|    14919602176|
| 1|    [opencl:gpu:0]|                 Intel(R) Iris(R) Xe Graphics|       3.0|         80|     512|     32|    14919602176|
| 2|    [opencl:cpu:0]|          12th Gen Intel(R) Core(TM) i5-1240P|       3.0|         16|    8192|     64|    16373895168|
| 3|    [opencl:acc:0]|               Intel(R) FPGA Emulation Device|       1.2|         16|67108864|     64|    16373895168|
check_allow_gpu_index error: device_index:0 is out of range: [0--2]
check_allow_gpu_index error: device_index:0 is out of range: [0--2]
Segmentation fault

any idea on this? facing the same problem

cc @abhilash1910

@barolo is it using latest master? Will take a look.

@barolo is it using latest master? Will take a look.

Yes, but it was a month ago. I'll recheck tonight

@barolo is it using latest master? Will take a look.

This is still present on latest master.

I tried it recently and it still seems like it is happening. If I comment out the function referenced, check_allow_gpu_index, which does the device_id checking and we stick with using 0 which points to my GPU's Level Zero instance, the end result is still hitting a segmentation fault.

@abhilash1910 hello, were you able to reproduce this? 😃

Yes will start on this shortly, appreciate the ping. Thanks. Mainly due to calling of init backend, which needs update.

Yes will start on this shortly, appreciate the ping. Thanks. Mainly due to calling of init backend, which needs update.

And I appreciate you working on this, thank you!

Been a while, but I can report that this got solved with all the updates to the SYCL backend that went into llama.cpp that got synced up to whisper.cpp and I no longer have issues with using SYCL and this particular error.

Same, can be closed

Can confirm, closing it.