issues
search
aws
/
sagemaker-huggingface-inference-toolkit
Apache License 2.0
235
stars
60
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Support load_lora_weights in inference API deploy
#131
haktan-suren
opened
1 month ago
0
Remove Conversation pipeline utils
#130
ed-berry
closed
1 month ago
4
SageMaker fails because Conversation object is not found
#129
adrihercer
opened
3 months ago
6
Can’t create an inference service for models that depend on packages i.e. `espeak`
#128
ghubnerr
opened
3 months ago
0
Update README.md
#127
dil-bhantos
closed
3 months ago
0
Custom Inference Code - model_fn() takes more positional argument
#126
dil-bhantos
opened
3 months ago
0
feat(initialize): default to first GPU when gpu_id not provided
#125
btruhand
opened
4 months ago
0
fix(setup): install either tensorflow-macos or tensorflow depending on platform processor
#124
btruhand
opened
4 months ago
0
Sagemaker HuggingfaceModel fails on phi3 model deployment
#123
manikawnth
opened
4 months ago
2
Sagemaker endpoint inference Fails when following a tutorial
#122
IoannisDem
opened
4 months ago
0
update version
#121
philschmid
closed
4 months ago
0
Add Inferentai2 and Optimum Neuron Support
#120
philschmid
closed
4 months ago
0
device kernel image is invalid
#119
geraldstanje1
opened
4 months ago
0
Add warning message to log this error.
#118
chen3933
closed
3 months ago
9
Sagemaker endpoint doesn't use GPU (instance ml.g4dn.xlarge)
#117
jypucca
opened
5 months ago
1
Sagemaker inference not loading model weight from s3
#116
saichethan-a
opened
5 months ago
2
Make DEFAULT_HF_HUB_MODEL_EXPORT_DIRECTORY configurable
#115
pcolazurdo
opened
6 months ago
0
Log if handler service is using default or custom functions implementation
#114
aduverger
closed
5 months ago
3
Add support for additional tasks via HuggingFace TaskManager
#113
samruds
closed
6 months ago
0
ARCHITECTURES_2_TASK is limiting the tasks able to be deployed with HF DLC
#112
gwang111
closed
6 months ago
11
Endpoint creation completes before custom model_fn finishes loading resources
#111
Tripping-Hazard
opened
7 months ago
0
HF_TASK Enviournment Variable error
#110
316usman
opened
8 months ago
1
Support multiple return sequences
#109
Elanmarkowitz
opened
9 months ago
0
Sagemaker endpoint inferencing error with HF model loading from s3bucket with new transformer update
#108
miteshkotak
opened
10 months ago
5
🏷️ invalid
#107
pierrishm1987
opened
11 months ago
0
No support for multi-GPU
#106
parviste-fortum
opened
11 months ago
3
get_pipeline function passes Path object rather than PretrainedTokenizer
#105
jpang32
opened
1 year ago
0
Add diffusers utils
#104
philschmid
closed
10 months ago
5
Add context to handler functions
#103
sachanub
closed
1 year ago
1
Using custom inference script and models from Hub
#102
Tarun02
opened
1 year ago
1
Dummy PR
#101
sachanub
closed
1 year ago
0
Prioritize safetensors format and support sharded weights
#100
BaiqingL
closed
5 months ago
1
Where is the logic for detecting custom inference.py?
#99
BaiqingL
closed
1 year ago
6
How to enable Batch inference on AWS deployed Serverless model from Hub?
#98
jmparejaz
opened
1 year ago
1
How can I delpoy a model with AWS S3 and without downloading model from hunggingface via TGI image on Sagemaker?
#97
weiZhenkun
closed
1 year ago
2
Error on Sagemaker deployment for v1.0.1
#96
mer0mingian
closed
1 year ago
1
Release 2 2 0
#95
philschmid
closed
1 year ago
0
SageMaker deployment errors
#94
jonrossclaytor
opened
1 year ago
2
Sharded checkpoint support
#93
JimAllanson
closed
5 months ago
1
Add `optimum-neuron` pipeline support for zero code deployment.
#92
philschmid
closed
1 year ago
0
Dead Link for Available HF_Tasks
#91
dcsena
opened
1 year ago
1
[DOCS] List of available HF_TASK and default inference scripts
#90
austinmw
closed
1 year ago
4
How to access CustomAttributes in async inferece request input_fn
#89
dcdieci
opened
1 year ago
1
trust_remote_code=True in new Hugging Face LLM Inference Container for Amazon SageMaker
#88
krokoko
closed
1 year ago
2
InternalServerException at runtime
#87
krokoko
closed
7 months ago
3
Update version to 2.1.2
#86
maaquib
closed
1 year ago
0
Support passing model_kwargs to pipeline
#85
lukealexmiller
opened
1 year ago
1
Add support for JSON encoding `torch.tensor` to keep it consistent with sagemaker-inference-toolkit
#84
maaquib
closed
1 year ago
0
Data format for inference
#83
alvaropp
opened
1 year ago
1
Update mms_model_server.py
#81
ShubhamRaiGit
closed
1 year ago
0
Next