Add qwen config and and input config simplification #1190
Merged
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
|
once this lands we should get https://github.com/basetenlabs/docs.baseten.co/pull/99 out |
joostinyi
commented
Oct 17, 2024
| @@ -75,7 +75,6 @@ class TrussTRTLLMBuildConfiguration(BaseModel): | |||
| plugin_configuration: TrussTRTLLMPluginConfiguration = ( | |||
| TrussTRTLLMPluginConfiguration() | |||
| ) | |||
| use_fused_mlp: bool = False | |||
There was a problem hiding this comment.
moved to plugin config – defaulted to true
joostinyi
added a commit
to basetenlabs/truss-examples
that referenced
this pull request
Oct 29, 2024
With newer versions of TRT-LLM and our engine builder, the `max_input_len` and `max_output_len` configurations have been deprecated in favor of `max_seq_len`. This PR should be landed after basetenlabs/truss#1190 and the lock file should be updated to pick up config changes from `truss` mainline. Passing run [here](https://github.com/basetenlabs/truss-examples/actions/runs/11562846363/job/32188633491)
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Outdated suggestions cannot be applied.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.
🚀 What
max_input_lenandmax_output_lenconfiguration in favor ofmax_seq_lenmax_batch_sizeandmax_num_tokens💻 How
🔬 Testing