[PPDiffuers] Add CycleDiffusion based on FastDeploy #4945
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
Codecov Report
@@ Coverage Diff @@
## develop #4945 +/- ##
===========================================
+ Coverage 46.35% 48.96% +2.60%
===========================================
Files 448 455 +7
Lines 64646 66517 +1871
===========================================
+ Hits 29965 32567 +2602
+ Misses 34681 33950 -731
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
joey12300
changed the title
guoshengCS
previously approved these changes
Feb 28, 2023
| untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids | ||
|
|
||
| if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not paddle.equal_all( | ||
| text_input_ids, untruncated_ids |
There was a problem hiding this comment.
text_input_ids和untruncated_ids是np的，这里paddle.equal_all是否需要用np的呢
| ).prev_sample | ||
| if i == len(timesteps) - 1: | ||
| # sync for accuracy it/s measure | ||
| paddle.device.cuda.synchronize() |
There was a problem hiding this comment.
这里是否是必须的呢，看其他的pipelile包括FastDeploy pipeline里没有这个
There was a problem hiding this comment.
主要保证多流kernel异步发射的最终结果正确，需要同步
jiangjiajun
suggested changes
Feb 28, 2023
| if use_fp16: | ||
| option.trt_option.enable_fp16 = True | ||
| cache_file = os.path.join(model_dir, model_prefix, "inference.trt") | ||
| option.set_trt_cache_file(cache_file) |
There was a problem hiding this comment.
看到上面的代码已经开始在使用1.0.4的API了， option.paddle_infer_option，那就统一都开始切为新版本API吧
改为option.trt_option.serialize_file = cache_file
| option.set_trt_cache_file(cache_file) | ||
| # Need to enable collect shape for ernie | ||
| if dynamic_shape is not None: | ||
| option.enable_paddle_trt_collect_shape() |
There was a problem hiding this comment.
option.paddle_infer_option.collect_trt_shape = True
| option.enable_paddle_trt_collect_shape() | ||
| for key, shape_dict in dynamic_shape.items(): | ||
| option.set_trt_input_shape( | ||
| key, |
There was a problem hiding this comment.
option.trt_option.set_shape(name, min, opt, max)
| option.use_lite_backend() | ||
| if device == "huawei_ascend_npu": | ||
| option.use_ascend() | ||
| option.set_lite_device_names(["huawei_ascend_npu"]) |
| option.set_lite_device_names(["huawei_ascend_npu"]) | ||
| option.set_lite_model_cache_dir(os.path.join(model_dir, model_prefix)) | ||
| option.set_lite_context_properties( | ||
| "HUAWEI_ASCEND_NPU_SELECTED_DEVICE_IDS={};HUAWEI_ASCEND_NPU_PRECISION_MODE=allow_mix_precision".format( |
There was a problem hiding this comment.
option.paddle_lite_option.nnadapter_model_cache_dir = os.path.join(model_dir, model_prefix)
option.paddle_lite_option.nnadapter_context_properties = "HUAWEI_ASCEND_NPU_SELECTED_DEVICE_IDS={};HUAWEI_ASCEND_NPU_PRECISION_MODE=allow_mix_precision".format(device_id)
| option = fd.RuntimeOption() | ||
| option.use_trt_backend() | ||
| option.use_gpu(device_id) | ||
| option.enable_trt_fp16() |
There was a problem hiding this comment.
option.trt_option.enable_fp16 = True
| option.use_trt_backend() | ||
| option.use_gpu(device_id) | ||
| option.enable_trt_fp16() | ||
| option.set_trt_max_workspace_size(workspace) |
There was a problem hiding this comment.
option.trt_option.max_workspace_size = workspace
| option.set_trt_max_workspace_size(workspace) | ||
| if dynamic_shape is not None: | ||
| for key, shape_dict in dynamic_shape.items(): | ||
| option.set_trt_input_shape( |
| onnx_file = os.path.join(model_dir, model_prefix, "inference.onnx") | ||
| option.set_model_path(onnx_file, model_format=ModelFormat.ONNX) | ||
| cache_file = os.path.join(model_dir, model_prefix, "inference.trt") | ||
| option.set_trt_cache_file(cache_file) |
There was a problem hiding this comment.
option.trt_option.serialize_file = cache_file
guoshengCS
approved these changes
Mar 1, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
New features
PR changes
Models
Description
Add CycleDiffusion based on FastDeploy.
Benchmark
Run CycleDiffusionPipeline 10 times and get average latency to compare the performace between FastDeploy version and pytorch version.
Average latency