This message was deleted.
# ask-for-help
s
This message was deleted.
👀 1
🏁 1
🍱 1
b
Where are you deploying to?
g
@Bo Using the docker container to deploy to GKE cluster.
Tried to get Yatai going, but decided to go old-fashioned. On the docket for later.
Copy code
2022-10-02T23:44:20+0000 [INFO] [cli] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:21+0000 [INFO] [cli] Environ for worker 0: set CUDA_VISIBLE_DEVICES to 0
2022-10-02T23:44:21+0000 [INFO] [cli] Starting production BentoServer from "/home/bentoml/bento" running on <http://0.0.0.0:3000> (Press CTRL+C to quit)
2022-10-02T23:44:23+0000 [INFO] [api_server:2] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:23+0000 [INFO] [api_server:5] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:23+0000 [INFO] [api_server:7] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:23+0000 [INFO] [api_server:6] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:4] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:8] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:1] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:11] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:12] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:9] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [runner:stable_diffusion_runner:1] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:3] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
2022-10-02T23:44:24+0000 [INFO] [api_server:10] Service loaded from Bento directory: bentoml.Service(tag="stable_diffusion_fp16:ysyakjscu2gc34xy", path="/home/bentoml/bento/")
/usr/local/lib/python3.9/dist-packages/torch/cuda/__init__.py:146: UserWarning:
A100-SXM4-40GB MIG 3g.20gb with CUDA capability sm_80 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70.
If you want to use the A100-SXM4-40GB MIG 3g.20gb GPU with PyTorch, please check the instructions at <https://pytorch.org/get-started/locally/>
Full trace.
Trying now with
index-url
and
extra-index-url
as
<https://download.pytorch.org/whl/cu116>
. But it's a bit of a trial and error situation, didn't know if anyone had a ready answer.
a
Hi Greg, can you send the
docker
command you are using?
g
@Aaron Pham @Bo the index URLs w/ a
--no-cache
during
containerize
ended up being the trick! Thanks all.
👍 1