-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
docs: Re-structure User Guides for Discoverability #7807
base: main
Are you sure you want to change the base?
Conversation
|
||
# Add any paths that contain custom static files (such as style sheets) here, | ||
# relative to this directory. They are copied after the builtin static files, | ||
# so a file named "default.css" will overwrite the builtin "default.css". | ||
html_static_path = ["_static"] | ||
html_css_files = ["custom.css"] | ||
#html_css_files = ["custom.css"] # Not needed with new theme |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
#html_css_files = ["custom.css"] # Not needed with new theme |
#"json_url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/" | ||
#"docs/_static/switcher.json", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
#"json_url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/" | |
#"docs/_static/switcher.json", |
@@ -31,7 +31,7 @@ | |||
Clients can communicate with Triton using either an [HTTP/REST | |||
protocol](#httprest-and-grpc-protocols), a [GRPC | |||
protocol](#httprest-and-grpc-protocols), or by an [in-process C | |||
API](#in-process-triton-server-api) or its | |||
API](inprocess_c_api.md#in-process-triton-server-api) or its |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
update copyrights
"url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/" | ||
}, | ||
{ | ||
"name": "2.50 (stable)", | ||
"version": "2.50", | ||
"url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/" | ||
}, | ||
{ | ||
"name": "2.49", | ||
"version": "2.49", | ||
"url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we have different urls available for each version?
@@ -0,0 +1,10 @@ | |||
######## | |||
State Management |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
On the rendering, the State Management
section feels unnecessarily nested. It's a single indirection to the Implicit State Management page with no other info/links.
Maybe the State Management tab/page can also provide a link to the (1) Sequence Batch Scheduler and (2) Stateful Model sections/docs?
State Management
- Stateful Models (link)
- Implicit State Management (link)
- Sequence Batch Scheduler (link)
Scheduler <../user_guide/scheduler.md> | ||
Batcher <../user_guide/batcher.md> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think these could probably be joined into one Scheduling & Batching
section
Scheduling & Batching
- Default Scheduler
- Ensemble Scheduler
- Dynamic Batch Scheduler
- Sequence Batch Scheduler
- Custom Batching Strategies
![Triton Mult-Model Parallel Execution | ||
Diagram](images/multi_model_parallel_exec.png) | ||
|
||
# Models And Schedulers |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This Model Execution doc feels a bit strange. The concurrent execution section at the top makes sense, but the following sections on schedulers, stateless, control inputs, etc. feel like they don't belong in the same category/doc.
Thanks for submitting a PR to Triton!
Please go the the
Preview
tab above this description box and select the appropriate sub-template:If you already created the PR, please replace this message with one of
and fill it out.