[Platform] Replace torch.cuda.mem_get_info with torch.accelerator.get_memory_info (#44825)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com> Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
This commit is contained in:
@@ -701,7 +701,7 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
start_time = time.perf_counter()
|
||||
gc.collect()
|
||||
torch.accelerator.empty_cache()
|
||||
start_free_gpu_memory = torch.cuda.mem_get_info()[0]
|
||||
start_free_gpu_memory = torch.accelerator.get_memory_info()[0]
|
||||
|
||||
with self.maybe_setup_dummy_loras(self.lora_config):
|
||||
attn_states = self.cudagraph_manager.capture(
|
||||
@@ -720,7 +720,7 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
self.speculator.capture(attn_states)
|
||||
|
||||
end_time = time.perf_counter()
|
||||
end_free_gpu_memory = torch.cuda.mem_get_info()[0]
|
||||
end_free_gpu_memory = torch.accelerator.get_memory_info()[0]
|
||||
elapsed_time = end_time - start_time
|
||||
cuda_graph_size = start_free_gpu_memory - end_free_gpu_memory
|
||||
# This usually takes 5~20 seconds.
|
||||
|
||||
Reference in New Issue
Block a user