One of the recent PRs introduced an error(see below) causing the model loading to fail when the triton server gets deployed.
Error Log:
I0715 04:06:56.609115 1 server.cc:674]
+-----------+---------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model | Version | Status |
+-----------+---------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| llama2 | 1 | READY |
| llama3 | 1 | UNAVAILABLE: Invalid argument: instance group llama3_0 of model llama3 specifies invalid or unsupported gpu id 2. GPUs with at least the minimum required CUDA compute compatibility of 6.000000 are: 0 |
| mistral7b | 1 | UNAVAILABLE: Invalid argument: instance group mistral7b_0 of model mistral7b specifies invalid or unsupported gpu id 1. GPUs with at least the minimum required CUDA compute compatibility of 6.000000 are: 0 |
+-----------+---------
This PR fixes the above issue.
🛑 Please open an issue first to discuss any significant work and flesh out details/direction - we would hate for your time to be wasted.
Consult the CONTRIBUTING guide for submitting pull-requests.
Motivation
More
[x] Yes, I have tested the PR using my local account setup (Provide any test evidence report under Additional Notes)
[x] Mandatory for new blueprints. Yes, I have added a example to support my blueprint PR
[x] Mandatory for new blueprints. Yes, I have updated the website/docs or website/blog section for this feature
[x] Yes, I ran pre-commit run -a with this PR. Link for installing pre-commit locally
What does this PR do?
One of the recent PRs introduced an error(see below) causing the model loading to fail when the triton server gets deployed.
This PR fixes the above issue.
🛑 Please open an issue first to discuss any significant work and flesh out details/direction - we would hate for your time to be wasted. Consult the CONTRIBUTING guide for submitting pull-requests.
Motivation
More
website/docs
orwebsite/blog
section for this featurepre-commit run -a
with this PR. Link for installing pre-commit locallyFor Moderators
Additional Notes