Skip to content

Commit

Permalink
[docs] Adds option.max_output_size document (#1354)
Browse files Browse the repository at this point in the history
  • Loading branch information
frankfliu authored Dec 1, 2023
1 parent 1b4f2d1 commit e96dc67
Showing 1 changed file with 6 additions and 1 deletion.
7 changes: 6 additions & 1 deletion serving/docs/configurations_model.md
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,9 @@ option.disablePerSessionThreads=true
option.ortDevice=TensorRT/ROCM/CoreML
# Python model options
retry_threshold=10 # Mark model as failure after python process crashing 10 times
# Mark model as failure after python process crashing 10 times
retry_threshold=10
option.pythonExecutable=python3
option.entryPoint=deepspeed.py
option.handler=hanlde
Expand All @@ -72,6 +74,9 @@ option.rolling_batch=auto
option.max_rolling_batch_size=64
option.paged_attention=false
option.max_rolling_batch_prefill_tokens=1088
# max output size in bytes, default to 60M
option.max_output_size=67108864
```

Most of the options can also be overriden by an environment variable with the `OPTION_` prefix and all caps.
Expand Down

0 comments on commit e96dc67

Please sign in to comment.