enable cpu offloading of new pipelines on XPU & use device agnostic empty to make pipelines work on XPU #11671
Conversation
| @@ -193,7 +193,7 @@ def __init__( | |||
| def enable_xformers_memory_efficient_attention(self, attention_op: Optional[Callable] = None): | |||
| self.decoder_pipe.enable_xformers_memory_efficient_attention(attention_op) | |||
|
|
|||
| def enable_sequential_cpu_offload(self, gpu_id: Optional[int] = None, device: Union[torch.device, str] = "cuda"): | |||
| def enable_sequential_cpu_offload(self, gpu_id: Optional[int] = None, device: Union[torch.device, str] = None): | |||
There was a problem hiding this comment.
per discussion in this PR #11288, we change the default to None, so cpu_offloading can work on other accelerators like XPU w/ application code change.
There was a problem hiding this comment.
with such changes, cases like tests/pipelines/wuerstchen/test_wuerstchen_combined.py::WuerstchenCombinedPipelineFastTests::test_cpu_offload_forward_pass_twice, tests/pipelines/kandinsky2_2/test_kandinsky_combined.py::KandinskyV22PipelineImg2ImgCombinedFastTests::test_cpu_offload_forward_pass_twice can pass on XPU
|
@a-r-r-o-w @DN6 , pls help review, thx very much. |
|
@bot /style |
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
| device_mod = getattr(torch, self.device.type, None) | ||
| if hasattr(device_mod, "empty_cache") and device_mod.is_available(): | ||
| device_mod.empty_cache() # otherwise we don't see the memory savings (but they probably exist) | ||
| empty_device_cache(orig_device_type) | ||
|
|
There was a problem hiding this comment.
@DN6 , the original code has a bug, the empty_cache will not be executed.
The logic is like: check module's device type w/ self.device.type, at this time, it's "cuda" or "xpu", then it goes to the if scope, then it put module to cpu w/ to, after this, the self.device.type will be "cpu". So, "device_mod" will be torch.cpu, it has no empty_cache, so the following check will not pass, so empty_cache will not be called, so no empty_cache behavior.
I changed the code to make it will empty_cache of device, pls review in case that's not what in your design.
PS. I attached the PR which changes to current code here: #4191
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
No description provided.