Segfault during inference

Crashed Thread:        23

Exception Type:        EXC_BAD_ACCESS (SIGSEGV)
Exception Codes:       KERN_INVALID_ADDRESS at 0x0000000000000700
Exception Codes:       0x0000000000000001, 0x0000000000000700

Termination Reason:    Namespace SIGNAL, Code 11 Segmentation fault: 11
Terminating Process:   exc handler [49912]


Thread 23 Crashed:
0   AGXMetalG13X                  	       0x32128d734 -[AGXG13XFamilyCommandBuffer tryCoalescingPreviousComputeCommandEncoderWithConfig:nextEncoderClass:] + 180
1   AGXMetalG13X                  	       0x32128d618 -[AGXG13XFamilyCommandBuffer computeCommandEncoderWithConfig:] + 84
2   AGXMetalG13X                  	       0x32128d544 -[AGXG13XFamilyCommandBuffer computeCommandEncoderWithDispatchType:] + 136
3   libmlx.dylib                  	       0x32351dda8 mlx::core::metal::CommandEncoder::CommandEncoder(mlx::core::metal::DeviceStream&) + 140
4   libmlx.dylib                  	       0x3235203a8 mlx::core::metal::Device::get_command_encoder(int) + 284
5   libmlx.dylib                  	       0x323559640 mlx::core::RandomBits::eval_gpu(std::__1::vector<mlx::core::array, std::__1::allocator<mlx::core::array>> const&, mlx::core::array&) + 484
6   libmlx.dylib                  	       0x32355605c mlx::core::metal::eval(mlx::core::array&) + 192
7   libmlx.dylib                  	       0x322b0608c mlx::core::eval_impl(std::__1::vector<mlx::core::array, std::__1::allocator<mlx::core::array>>, bool) + 4736
8   libmlx.dylib                  	       0x322b06c58 mlx::core::async_eval(std::__1::vector<mlx::core::array, std::__1::allocator<mlx::core::array>>) + 112
9   core.cpython-310-darwin.so    	       0x320219d78 0x320180000 + 630136

Environment:

import numpy as np
import mlx.core as mx
import mlx_whisper
import platform

print(f"numpy: {np.__version__}")
print(f"mlx: {mx.__version__}")
print(f"mlx_whisper: {mlx_whisper.__version__}")
print(f"macOS {platform.mac_ver()}")

Prints:

numpy: 1.26.4
mlx: 0.24.1
mlx_whisper: 0.4.1
macOS ('15.0.1', ('', '', ''), 'arm64')

Tried to reproduce letting it run overnight transcribing many hours, no luck. Seen it happen a few times now though.

Thanks for all your great work!

Start with the reported mlx_whisper inference path and the mlx.core GPU evaluation stack, especially RandomBits::eval_gpu in libmlx.dylib, using the listed Apple Silicon, macOS, and package versions. Reproduce the long-running transcription workload, then isolate the trigger and verify a fix; the issue names no repository files or tests.