[object Object]

← back to Exo

Update main.py: Default timeout 90->900

dbf40d78373ae47e9199a92359fc2874854525e4 · 2024-10-27 23:12:17 -0700 · FFAMax

On slow setups (~1 token per second) average response may take ~600-1000 tokens. In most cases it will lead to timeout (network error which is not). Fixing to reduce exceptions. Who looking for better performance and know what to do need adjust with a knowledge how it will impact. By default making it will work for most cases.

Files touched

Diff

commit dbf40d78373ae47e9199a92359fc2874854525e4
Author: FFAMax <ffamax@gmail.com>
Date:   Sun Oct 27 23:12:17 2024 -0700

    Update main.py: Default timeout 90->900
    
    On slow setups (~1 token per second) average response may take ~600-1000 tokens. In most cases it will lead to timeout (network error which is not). Fixing to reduce exceptions. Who looking for better performance and know what to do need adjust with a knowledge how it will impact. By default making it will work for most cases.
---
 exo/main.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exo/main.py b/exo/main.py
index 90bcc73c..b8bdb152 100644
--- a/exo/main.py
+++ b/exo/main.py
@@ -43,7 +43,7 @@ parser.add_argument("--discovery-timeout", type=int, default=30, help="Discovery
 parser.add_argument("--discovery-config-path", type=str, default=None, help="Path to discovery config json file")
 parser.add_argument("--wait-for-peers", type=int, default=0, help="Number of peers to wait to connect to before starting")
 parser.add_argument("--chatgpt-api-port", type=int, default=8000, help="ChatGPT API port")
-parser.add_argument("--chatgpt-api-response-timeout", type=int, default=90, help="ChatGPT API response timeout in seconds")
+parser.add_argument("--chatgpt-api-response-timeout", type=int, default=900, help="ChatGPT API response timeout in seconds")
 parser.add_argument("--max-generate-tokens", type=int, default=10000, help="Max tokens to generate in each request")
 parser.add_argument("--inference-engine", type=str, default=None, help="Inference engine to use (mlx, tinygrad, or dummy)")
 parser.add_argument("--disable-tui", action=argparse.BooleanOptionalAction, help="Disable TUI")

← d4e26fcb Update device_capabilities.py  ·  back to Exo  ·  fix flops parsing eb8a444e →