Last active
January 27, 2024 00:25
-
-
Save zachgk/93177fc4391597458f59067536bf2178 to your computer and use it in GitHub Desktop.
Rubikon IB Mistral Var
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[test_name] | |
mistral | |
[container] | |
deepjavalibrary/djl-serving:0.25.0-deepspeed | |
[vars] | |
CONCURRENCY={1,16,32} | |
[serving_properties] | |
engine=Python | |
option.tensor_parallel_degree=1 | |
option.rolling_batch=vllm | |
option.model_id=mistralai/Mistral-7B-v0.1 | |
option.max_rolling_batch_size=32 | |
[aws_curl] | |
TOKENIZER=mistralai/Mistral-7B-v0.1 ./awscurl -c $CONCURRENCY -N 10 \ | |
-X POST http://127.0.0.1:8080/invocations \ | |
--connect-timeout 60 -H "Content-type: application/json" \ | |
-d '{"inputs":"The new movie that got Oscar this year","parameters":{"max_new_tokens":256, "do_sample":true}}' \ | |
-t -o /tmp/output.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment