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Outdated suggestions cannot be applied.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.
This PR adds supports for DBRX. DBRX is a Mixture-of-Experts (MoE) model trained by Databricks with 132B total parameters and 36B live parameters. More details about the model can be found at: DBRX Technical Blog
Model weights can be found in HF repo:
Model can be run with 16-bit (BF16 or FP16) or 8-bit (INT8 weight-only + INT8 KV Cache). Detailed instructions for building and running TensorRT engines in the README under
examples/dbrx
directory.Note: Given model has 132B total parameters, it is suggested to use mininum 4x80GB GPU cards to run 16-bit inference and 2x80GB GPUs for 8-bit inference.