-
### Willingness to contribute
Yes. I can contribute this feature independently.
### Proposal Summary
It is not possible to use a secure MLflow Deployments Server as backend for MLflow Prompt …
-
Hello,
I have a question regarding automatic ci/cd model builds. Do I need deploy from a ray cluster node or could I run from a remote bastion node ?
The [ray cluster documentation](https://do…
-
Hi,
I am trying to fine tune a pre-trained model of SSD500x500 provided [here](http://www.cs.unc.edu/%7Ewliu/projects/SSD/models_VGGNet_ilsvrc15_SSD_500x500.tar.gz) with my training set using 'ssd_pas…
-
# Problem statement
Usually model inference is expensive, especially for large models.
# Motivation
With the caching feature, we can
1. reduce the latency of model inference.
2. save the…
-
### Willingness to contribute
Yes. I can contribute this feature independently.
### Proposal Summary
MLflow Authentication REST API covers most of the required endpoints to manage user authenticati…
-
### Describe the bug
Looking to do a QAT of the TopdownPoseEstimator model, I skipped `RTMCCHead.predict` and `RTMCCHead.loss` to avoid errors during tracing. This model trains fine as a fake quantiz…
-
### Elasticsearch Version
8.15
### Installed Plugins
_No response_
### Java Version
_bundled_
### OS Version
Mac OS
### Problem Description
When creating an inference endpoi…
ppf2 updated
3 months ago
-
**Describe the bug**
The deploy.sh script fails after 30-40 minutes with error:
Unable to activate API service at this time. Please make sure the all the requirements for setting up vnet injection…
-
`tabpy-deploy-models` runs `SentimentAnalysis.py` which runs:
```
nltk.download("vader_lexicon")
nltk.download("punkt")
```
This fails if you are running in environments without direct connec…
-
我的测试脚本：
```
NPROC_PER_NODE=8 \
ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
HCCL_SOME_VARIABLE=value
swift infer \
--model_type '/data2/dxc/Qwen1.5-32B-Chat' \
--load_args_from_ckpt_dir …