Torchserve support for Intel GPUs #3132
Open
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
5 tasks
lxning
reviewed
May 13, 2024
Comment on lines
+949
to
+967
| }catch (IOException | InterruptedException e) { | ||
| System.out.println("nvidia-smi not available or failed: " + e.getMessage()); | ||
| } | ||
| try { | ||
| Process process = Runtime.getRuntime().exec("xpu-smi discovery --dump 1"); | ||
| int ret = process.waitFor(); | ||
| if (ret != 0) { | ||
| return 0; | ||
| } | ||
| List<String> list = | ||
| IOUtils.readLines(process.getInputStream(), StandardCharsets.UTF_8); | ||
| if (list.isEmpty() || !list.get(0).contains("Device ID")) { | ||
| throw new AssertionError("Unexpected xpu-smi response."); | ||
| } | ||
| for (int i = 1; i < list.size(); i++) { | ||
| gpuIds.add(Integer.parseInt(list.get(i))); | ||
| } | ||
| }catch (IOException | InterruptedException e) { | ||
| System.out.println("xpu-smi not available or failed: " + e.getMessage()); |
There was a problem hiding this comment.
Is Intel GPU also set CUDA_VISIBLE_DEVICES? If not, this part code will not be executed.
ts/torch_handler/base_handler.py
Outdated
| @@ -370,7 +377,10 @@ def inference(self, data, *args, **kwargs): | |||
| Torch Tensor : The Predicted Torch Tensor is returned in this function. | |||
| """ | |||
| with torch.inference_mode(): | |||
| marshalled_data = data.to(self.device) | |||
| if IPEX_AVAILABLE and IPEX_GPU: # IPEX GPU | |||
| marshalled_data = data.to("xpu") | |||
There was a problem hiding this comment.
Thank you for the suggestion. We have updated this.
| @@ -90,6 +92,36 @@ Add the following lines in `config.properties` to use launcher with its default | |||
| cpu_launcher_enable=true | |||
| ``` | |||
|
|
|||
| ## TorchServe with Intel® Extension for PyTorch* and Intel GPUs | |||
There was a problem hiding this comment.
Can you please provide the information link about intel GPU performance gain?
This reverts commit 9188deb.
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.
Description
This PR will enable torchserve to leverage Intel GPU devices. This adds a config ipex_gpu_enable, to allow gpu enablement in base_handler.py
Type of change
Please delete options that are not relevant.
Checklist: