Giters
hpcaitech
/
EnergonAI
Large-scale model inference.
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
629
Watchers:
23
Issues:
50
Forks:
90
hpcaitech/EnergonAI Issues
How to inference BLOOM-176B by multi-node multi-card?
Updated
8 months ago
Comments count
2
关于示例代码版本落后,无法运行等问题About the example code version backward, can not run and other issues
Updated
8 months ago
Comments count
7
[bug] The InferenceEngine used in the example for distributed inference cannot be imported.
Updated
9 months ago
Support GPT BigCode (bigcode/starcoder, bigcode/gpt_bigcode-santacoder, etc.)
Updated
10 months ago
Comments count
1
OPT-125m problem
Updated
10 months ago
Location of logs
Closed
10 months ago
Docker cannot find the parent image defined in `docker/Dockerfile`
Updated
10 months ago
Does EnergonAI support accelerated inference for segmenting anything?
Updated
a year ago
EnergonAI running OPT reasoning example: When encountering a client request, the server is blocked and cannot return the result
Updated
a year ago
Comments count
1
Failed to load pre-trained model weights for OPT_125M
Closed
a year ago
Comments count
2
Where is InferenceEngine definition?
Updated
a year ago
question about load model state_dict in multi-gpus
Closed
a year ago
Comments count
2
Is there an example of the http client?
Updated
a year ago
Comments count
1
Concrete doc of this project
Updated
a year ago
Comments count
1
can't find server.sh
Updated
a year ago
Comments count
3
_pickle.UnpicklingError: invalid load key, '{'.
Updated
a year ago
Comments count
4
Why does it unreadable generated by OPT-30B inferring with EnergonAI
Closed
a year ago
Comments count
11
CUDA error: no kernel image is available for execution on the device
Updated
a year ago
Comments count
3
OPT inference
Updated
a year ago
Comments count
2
Where is InferenceEngine definition?
Updated
a year ago
Comments count
2
an error caused by running the example of the opt
Updated
a year ago
Comments count
4
Cannot run opt 125m examples with latest energonai docker images
Updated
a year ago
Comments count
2
How to use dynamic batch features
Updated
a year ago
Comments count
1
OPT demo TEST
Updated
a year ago
Comments count
2
fail to install EnergonAI
Updated
a year ago
Comments count
3
Is there any examples of using offload feature in GPT/BLOOM/OPT inference?
Updated
a year ago
Comments count
1
miss cache error when pose generation opt
Updated
a year ago
Comments count
2
failure to compile energonai by the command : python setup.py build
Updated
a year ago
Comments count
1
Doesn't run gpt reference?
Updated
a year ago
Comments count
1
Does not support Cuda 10.2 ?
Updated
a year ago
Comments count
1
Not compatible with the latest version of transformers? (4.26.1)
Updated
a year ago
Comments count
2
Can not start the Bloom server
Updated
a year ago
Comments count
3
Maybe you should add license for using OneFlow's LayerNorm Kernel implement?
Closed
a year ago
Comments count
2
Failed to load OPT-30B checkpoint
Closed
a year ago
Comments count
2
Support OPT-IML model
Closed
a year ago
Comments count
1
Detected RRef Leaks during shutdown, empty pipe, tests_engine failed
Updated
a year ago
Comments count
1
trpc.rpc_sync consumed most time
Updated
a year ago
RuntimeError('FusedLayerNormAffineFunction requires cuda extensions')
Updated
a year ago
torch.load() hangs indefinitely when reading OPT pre-trained model weights
Updated
2 years ago
Comments count
1
need guidelines on converting OPT-17B checkpoint
Closed
2 years ago
does EnergonAI support gpt model with int8 quantitation in model parallel?
Updated
2 years ago
Comments count
1
[RFC] Async engine and pipeline based on RPC
Closed
2 years ago
Comments count
1
num_beams for beam search
Updated
2 years ago
Comments count
1
inference of pre-trained model
Updated
2 years ago
Comments count
1
Remove hard code directory path
Updated
2 years ago
Provide a docker service
Closed
2 years ago
OPT inference generate example
Updated
2 years ago
Comments count
1
Missing energonai_linear_func in setup.py
Updated
2 years ago
Comments count
1
Connection refused on docker exposed port
Updated
2 years ago
Comments count
1
[Feature]: Automatic Pipeline Parallelism
Updated
2 years ago