Panagiotis Xanthopoulos

CUDA out of memory due to huge memory allocation request

5

### What happened? I compiled GPT and tried to run it using `iree-run-module`. It errored with the following message: ``` iree/runtime/src/iree/hal/drivers/cuda/memory_pools.c:236: RESOURCE_EXHAUSTED; CUDA error 'CUDA_ERROR_OUT_OF_MEMORY' (2): out of memory; while...

[Runtime] Bug in tracing execution of module for allocations larger than 4GiB.

2

### What happened? Hi. I'm trying to compile and run a Phi model to analyze memory allocation (constants, transients, etc.). While using `iree-run-module`, I encountered what seems to be a...