Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Diffusion Fast Example #2902

Merged
merged 16 commits into from
Jan 31, 2024
Merged

Diffusion Fast Example #2902

merged 16 commits into from
Jan 31, 2024

Conversation

agunapal
Copy link
Collaborator

@agunapal agunapal commented Jan 23, 2024

Description

This is an example showing how to use Diffusion Fast with TorchServe

Fixes #(issue)

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

Feature/Issue validation/testing

  • Model loading
2024-01-23T20:47:59,877 [WARN ] main org.pytorch.serve.util.ConfigManager - Your torchserve instance can access any URL to load models. When deploying to production, make sure to limit the set of allowed_urls in config.properties
2024-01-23T20:47:59,879 [INFO ] main org.pytorch.serve.servingsdk.impl.PluginsManager - Initializing plugins manager...
2024-01-23T20:47:59,926 [INFO ] main org.pytorch.serve.metrics.configuration.MetricConfiguration - Successfully loaded metrics configuration from /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/ts/configs/metrics.yaml
2024-01-23T20:48:00,001 [INFO ] main org.pytorch.serve.ModelServer - 
Torchserve version: 0.9.0
TS Home: /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages
Current directory: /home/ubuntu/serve/examples/image_generation/diffusion_fast
Temp directory: /tmp
Metrics config path: /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/ts/configs/metrics.yaml
Number of GPUs: 1
Number of CPUs: 8
Max heap size: 7936 M
Python executable: /home/ubuntu/anaconda3/envs/ts_export_aot/bin/python
Config file: config.properties
Inference address: http://127.0.0.1:8080
Management address: http://127.0.0.1:8081
Metrics address: http://127.0.0.1:8082
Model Store: /home/ubuntu/serve/examples/image_generation/diffusion_fast/model_store
Initial Models: diffusion_fast
Log dir: /home/ubuntu/serve/examples/image_generation/diffusion_fast/logs
Metrics dir: /home/ubuntu/serve/examples/image_generation/diffusion_fast/logs
Netty threads: 0
Netty client threads: 0
Default workers per model: 1
Blacklist Regex: N/A
Maximum Response Size: 655350000
Maximum Request Size: 6553500
Limit Maximum Image Pixels: true
Prefer direct buffer: false
Allowed Urls: [file://.*|http(s)?://.*]
Custom python dependency for model allowed: true
Enable metrics API: true
Metrics mode: LOG
Disable system metrics: false
Workflow Store: /home/ubuntu/serve/examples/image_generation/diffusion_fast/model_store
Model config: N/A
2024-01-23T20:48:00,007 [INFO ] main org.pytorch.serve.servingsdk.impl.PluginsManager -  Loading snapshot serializer plugin...
2024-01-23T20:48:00,023 [INFO ] main org.pytorch.serve.ModelServer - Loading initial models: diffusion_fast
2024-01-23T20:48:00,030 [INFO ] main org.pytorch.serve.archive.model.ModelArchive - createTempDir /tmp/models/560a5ef8426d4df193109f68505eff3d
2024-01-23T20:48:00,030 [INFO ] main org.pytorch.serve.archive.model.ModelArchive - createSymbolicDir /tmp/models/560a5ef8426d4df193109f68505eff3d/diffusion_fast
2024-01-23T20:48:00,041 [DEBUG] main org.pytorch.serve.wlm.ModelVersionedRefs - Adding new version 1.0 for model diffusion_fast
2024-01-23T20:48:00,041 [DEBUG] main org.pytorch.serve.wlm.ModelVersionedRefs - Setting default version to 1.0 for model diffusion_fast
2024-01-23T20:48:00,041 [INFO ] main org.pytorch.serve.wlm.ModelManager - Model diffusion_fast loaded.
2024-01-23T20:48:00,042 [DEBUG] main org.pytorch.serve.wlm.ModelManager - updateModel: diffusion_fast, count: 1
2024-01-23T20:48:00,048 [DEBUG] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerLifeCycle - Worker cmdline: [/home/ubuntu/anaconda3/envs/ts_export_aot/bin/python, /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/ts/model_service_worker.py, --sock-type, unix, --sock-name, /tmp/.ts.sock.9000, --metrics-config, /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/ts/configs/metrics.yaml]
2024-01-23T20:48:00,048 [INFO ] main org.pytorch.serve.ModelServer - Initialize Inference server with: EpollServerSocketChannel.
2024-01-23T20:48:00,125 [INFO ] main org.pytorch.serve.ModelServer - Inference API bind to: http://127.0.0.1:8080
2024-01-23T20:48:00,126 [INFO ] main org.pytorch.serve.ModelServer - Initialize Management server with: EpollServerSocketChannel.
2024-01-23T20:48:00,127 [INFO ] main org.pytorch.serve.ModelServer - Management API bind to: http://127.0.0.1:8081
2024-01-23T20:48:00,127 [INFO ] main org.pytorch.serve.ModelServer - Initialize Metrics server with: EpollServerSocketChannel.
2024-01-23T20:48:00,128 [INFO ] main org.pytorch.serve.ModelServer - Metrics API bind to: http://127.0.0.1:8082
Model server started.
2024-01-23T20:48:00,295 [WARN ] pool-3-thread-1 org.pytorch.serve.metrics.MetricCollector - worker pid is not available yet.
2024-01-23T20:48:01,029 [INFO ] pool-3-thread-1 TS_METRICS - CPUUtilization.Percent:0.0|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,030 [INFO ] pool-3-thread-1 TS_METRICS - DiskAvailable.Gigabytes:41.73371887207031|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,031 [INFO ] pool-3-thread-1 TS_METRICS - DiskUsage.Gigabytes:248.8172264099121|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,031 [INFO ] pool-3-thread-1 TS_METRICS - DiskUtilization.Percent:85.6|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,031 [INFO ] pool-3-thread-1 TS_METRICS - GPUMemoryUtilization.Percent:0.0|#Level:Host,DeviceId:0|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,032 [INFO ] pool-3-thread-1 TS_METRICS - GPUMemoryUsed.Megabytes:0.0|#Level:Host,DeviceId:0|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,032 [INFO ] pool-3-thread-1 TS_METRICS - GPUUtilization.Percent:0.0|#Level:Host,DeviceId:0|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,032 [INFO ] pool-3-thread-1 TS_METRICS - MemoryAvailable.Megabytes:30292.6484375|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,033 [INFO ] pool-3-thread-1 TS_METRICS - MemoryUsed.Megabytes:972.83203125|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,033 [INFO ] pool-3-thread-1 TS_METRICS - MemoryUtilization.Percent:4.5|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042881
2024-01-23T20:48:01,630 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - s_name_part0=/tmp/.ts.sock, s_name_part1=9000, pid=64042
2024-01-23T20:48:01,631 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Listening on port: /tmp/.ts.sock.9000
2024-01-23T20:48:01,639 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Successfully loaded /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/ts/configs/metrics.yaml.
2024-01-23T20:48:01,640 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - [PID]64042
2024-01-23T20:48:01,640 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Torch worker started.
2024-01-23T20:48:01,641 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Python runtime: 3.10.13
2024-01-23T20:48:01,641 [DEBUG] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - W-9000-diffusion_fast_1.0 State change null -> WORKER_STARTED
2024-01-23T20:48:01,645 [INFO ] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Connecting to: /tmp/.ts.sock.9000
2024-01-23T20:48:01,652 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Connection accepted: /tmp/.ts.sock.9000.
2024-01-23T20:48:01,655 [DEBUG] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Flushing req.cmd LOAD repeats 1 to backend at: 1706042881654
2024-01-23T20:48:01,657 [INFO ] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Looping backend response at: 1706042881656
2024-01-23T20:48:01,691 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - model_name: diffusion_fast, batchSize: 1
2024-01-23T20:48:02,299 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/transformers/utils/generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
2024-01-23T20:48:02,300 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG -   _torch_pytree._register_pytree_node(
2024-01-23T20:48:02,485 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
2024-01-23T20:48:02,485 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG -   _torch_pytree._register_pytree_node(
2024-01-23T20:48:02,502 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/diffusers/utils/outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
2024-01-23T20:48:02,502 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG -   torch.utils._pytree._register_pytree_node(
2024-01-23T20:48:03,728 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Enabled tensor cores
2024-01-23T20:48:03,728 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - proceeding without onnxruntime
2024-01-23T20:48:03,728 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Torch TensorRT not enabled
2024-01-23T20:48:03,731 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Using dtype: torch.bfloat16
2024-01-23T20:48:03,746 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - /home/ubuntu/anaconda3/envs/ts_export_aot/lib/python3.10/site-packages/diffusers/utils/outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
2024-01-23T20:48:03,747 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG -   torch.utils._pytree._register_pytree_node(
2024-01-23T20:48:03,749 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - 
2024-01-23T20:48:03,862 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
2024-01-23T20:48:04,058 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - Loading pipeline components...:  14%|█▍        | 1/7 [00:00<00:00,  8.89it/s]
2024-01-23T20:48:05,992 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - Loading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  6.19it/s]
2024-01-23T20:48:06,690 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - Loading pipeline components...:  43%|████▎     | 3/7 [00:02<00:03,  1.03it/s]
2024-01-23T20:48:06,752 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - Loading pipeline components...:  71%|███████▏  | 5/7 [00:02<00:01,  1.62it/s]
2024-01-23T20:48:06,752 [WARN ] W-9000-diffusion_fast_1.0-stderr MODEL_LOG - Loading pipeline components...: 100%|██████████| 7/7 [00:03<00:00,  2.33it/s]
2024-01-23T20:48:06,774 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Using a more numerically stable VAE.
2024-01-23T20:48:07,025 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Enabling fused QKV projections for both UNet and VAE.
2024-01-23T20:48:14,341 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Compile UNet.
2024-01-23T20:48:14,343 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Apply quantization to UNet.
2024-01-23T20:48:14,587 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Compile VAE.
2024-01-23T20:48:14,587 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Apply quantization to VAE.
2024-01-23T20:48:14,589 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Diffusion Fast model loaded successfully
2024-01-23T20:48:14,593 [INFO ] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Backend response time: 12936
2024-01-23T20:48:14,593 [DEBUG] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - W-9000-diffusion_fast_1.0 State change WORKER_STARTED -> WORKER_MODEL_LOADED
2024-01-23T20:48:14,594 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - WorkerLoadTime.Milliseconds:14548.0|#WorkerName:W-9000-diffusion_fast_1.0,Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042894
2024-01-23T20:48:14,594 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - WorkerThreadTime.Milliseconds:4.0|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706042894


  • Inference Test
 python query.py --url "http://localhost:8080/predictions/diffusion_fast" --prompt "a photo of an astronaut riding a horse on mars"
2024-01-23T20:52:21,077 [INFO ] epollEventLoopGroup-3-3 TS_METRICS - ts_inference_requests_total.Count:1.0|#model_name:diffusion_fast,model_version:default|#hostname:ip-172-31-11-40,timestamp:1706043141
2024-01-23T20:52:21,077 [DEBUG] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Flushing req.cmd PREDICT repeats 1 to backend at: 1706043141077
2024-01-23T20:52:21,077 [INFO ] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Looping backend response at: 1706043141077
2024-01-23T20:52:21,078 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Backend received inference at: 1706043141
2024-01-23T20:52:21,078 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Received text: 'a photo of an astronaut riding a horse on mars'
2024-01-23T20:52:21,079 [INFO ] W-9000-diffusion_fast_1.0-stdout org.pytorch.serve.wlm.WorkerLifeCycle - result=[METRICS]ts_handler_preprocess.Milliseconds:0.0982080027461052|#ModelName:diffusion_fast,Level:Model|#type:GAUGE|#hostname:ip-172-31-11-40,1706043141,9c21be9b-a618-4fd8-827a-f3a683adf9d4, pattern=[METRICS]
2024-01-23T20:52:24,822 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_LOG - Generated image: '[<PIL.Image.Image image mode=RGB size=768x768 at 0x7F168443C7F0>]'
2024-01-23T20:52:24,822 [INFO ] W-9000-diffusion_fast_1.0-stdout org.pytorch.serve.wlm.WorkerLifeCycle - result=[METRICS]ts_handler_inference.Milliseconds:3743.239990234375|#ModelName:diffusion_fast,Level:Model|#type:GAUGE|#hostname:ip-172-31-11-40,1706043144,9c21be9b-a618-4fd8-827a-f3a683adf9d4, pattern=[METRICS]
2024-01-23T20:52:26,086 [INFO ] W-9000-diffusion_fast_1.0-stdout org.pytorch.serve.wlm.WorkerLifeCycle - result=[METRICS]ts_handler_postprocess.Milliseconds:1263.381103515625|#ModelName:diffusion_fast,Level:Model|#type:GAUGE|#hostname:ip-172-31-11-40,1706043146,9c21be9b-a618-4fd8-827a-f3a683adf9d4, pattern=[METRICS]
2024-01-23T20:52:26,086 [INFO ] W-9000-diffusion_fast_1.0-stdout org.pytorch.serve.wlm.WorkerLifeCycle - result=[METRICS]HandlerTime.Milliseconds:5007.6|#ModelName:diffusion_fast,Level:Model|#type:GAUGE|#hostname:ip-172-31-11-40,1706043146,9c21be9b-a618-4fd8-827a-f3a683adf9d4, pattern=[METRICS]
2024-01-23T20:52:26,087 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_METRICS - HandlerTime.ms:5007.6|#ModelName:diffusion_fast,Level:Model|#hostname:ip-172-31-11-40,requestID:9c21be9b-a618-4fd8-827a-f3a683adf9d4,timestamp:1706043146
2024-01-23T20:52:26,087 [INFO ] W-9000-diffusion_fast_1.0-stdout org.pytorch.serve.wlm.WorkerLifeCycle - result=[METRICS]PredictionTime.Milliseconds:5007.67|#ModelName:diffusion_fast,Level:Model|#type:GAUGE|#hostname:ip-172-31-11-40,1706043146,9c21be9b-a618-4fd8-827a-f3a683adf9d4, pattern=[METRICS]
2024-01-23T20:52:26,087 [INFO ] W-9000-diffusion_fast_1.0-stdout MODEL_METRICS - PredictionTime.ms:5007.67|#ModelName:diffusion_fast,Level:Model|#hostname:ip-172-31-11-40,requestID:9c21be9b-a618-4fd8-827a-f3a683adf9d4,timestamp:1706043146
2024-01-23T20:52:27,652 [INFO ] W-9000-diffusion_fast_1.0 ACCESS_LOG - /127.0.0.1:53342 "POST /predictions/diffusion_fast HTTP/1.1" 200 6576
2024-01-23T20:52:27,652 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - Requests2XX.Count:1.0|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706043147
2024-01-23T20:52:27,652 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - ts_inference_latency_microseconds.Microseconds:6558096.239|#model_name:diffusion_fast,model_version:default|#hostname:ip-172-31-11-40,timestamp:1706043147
2024-01-23T20:52:27,653 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - ts_queue_latency_microseconds.Microseconds:80.1|#model_name:diffusion_fast,model_version:default|#hostname:ip-172-31-11-40,timestamp:1706043147
2024-01-23T20:52:27,653 [DEBUG] W-9000-diffusion_fast_1.0 org.pytorch.serve.job.RestJob - Waiting time ns: 80100, Backend time ns: 6575608057
2024-01-23T20:52:27,653 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - QueueTime.Milliseconds:0.0|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706043147
2024-01-23T20:52:27,653 [INFO ] W-9000-diffusion_fast_1.0 org.pytorch.serve.wlm.WorkerThread - Backend response time: 6557
2024-01-23T20:52:27,653 [INFO ] W-9000-diffusion_fast_1.0 TS_METRICS - WorkerThreadTime.Milliseconds:19.0|#Level:Host|#hostname:ip-172-31-11-40,timestamp:1706043147

Checklist:

  • Did you have fun?
  • Have you added tests that prove your fix is effective or that this feature works?
  • Has code been commented, particularly in hard-to-understand areas?
  • Have you made corresponding changes to the documentation?

@agunapal agunapal changed the title (WIP) Diffusion Fast Example Diffusion Fast Example Jan 26, 2024
@agunapal agunapal requested review from mreso and lxning January 26, 2024 20:28
Copy link
Collaborator

@lxning lxning left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we move this example into example/large_models and rename/move Download_model.py to example/large_models/utils/Download_stable_diffusion_model.py?

model_dir = properties.get("model_dir")

self.device = torch.device(
"cuda:" + str(properties.get("gpu_id"))
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the order needs to be changed b/c the input gpu_id is < 0 for cpu case.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

updated the logic

input_text = data.get("body")
if isinstance(input_text, (bytes, bytearray)):
input_text = input_text.decode("utf-8")
logger.info("Received text: '%s'", input_text)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this can be removed for prod

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

inputs, num_inference_steps=self.num_inference_steps, height=768, width=768
).images

logger.info("Generated image: '%s'", inferences)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ditto

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

responseTimeout: 3600
deviceType: "gpu"
handler:
model_weights: "./Base_Diffusion_model"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we change to model_path to align with the other LMI example style?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

@agunapal agunapal requested a review from lxning January 31, 2024 00:45
@agunapal agunapal added this pull request to the merge queue Jan 31, 2024
Merged via the queue into master with commit a797f8c Jan 31, 2024
13 checks passed
@agunapal agunapal deleted the examples/diffusion_fast branch February 2, 2024 17:31
@chauhang chauhang added this to the v0.10.0 milestone Feb 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants