Add setup instructions for TensorRT-LLM #789
Closed
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
dakinggg
reviewed
Dec 8, 2023
| 1. Convert an MPT HuggingFace checkpoint into the FasterTransformer format. | ||
| 2. Build a TensorRT engine with the FasterTransformer weights | ||
|
|
||
| Using this engine, you can utilize TensorRT-LLM for fast inference. If you would like to use TensorRT-LLM as an end-to-end solution for an inference service, you can utilize the built engine with an NVIDIA Triton server backend: an example server can be found in [this repository](https://github.com/triton-inference-server/tensorrtllm_backend/tree/v0.6.1) accompanying the most recent release. |
There was a problem hiding this comment.
was "built engine" supposed to be "built-in engine"?
There was a problem hiding this comment.
I'd rephrase it as "built TRT engine". Also, here again we should drop "most recent release" as suggested by Daniel above.
There was a problem hiding this comment.
@linden-li can you pls make the suggested changes here? also, update TRT LLM link to v0.7.1?
megha95
approved these changes
Dec 8, 2023
|
@megha95 can we merge this? |
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Outdated suggestions cannot be applied.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.
No description provided.