fix args for ensure_shard

29244c6369b4a81c13dd41fab6be20121642613b · 2025-01-05 02:33:25 +0000 · Alex Cheema

Files touched

M exo/api/chatgpt_api.py

Diff

commit 29244c6369b4a81c13dd41fab6be20121642613b
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Sun Jan 5 02:33:25 2025 +0000

    fix args for ensure_shard
---
 exo/api/chatgpt_api.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exo/api/chatgpt_api.py b/exo/api/chatgpt_api.py
index 4daa199d..ef963400 100644
--- a/exo/api/chatgpt_api.py
+++ b/exo/api/chatgpt_api.py
@@ -568,7 +568,7 @@ class ChatGPTAPI:
       if model_name not in model_cards: return web.json_response({"error": f"Invalid model: {model_name}. Supported models: {list(model_cards.keys())}"}, status=400)
       shard = build_base_shard(model_name, self.inference_engine_classname)
       if not shard: return web.json_response({"error": f"Could not build shard for model {model_name}"}, status=400)
-      asyncio.create_task(self.node.inference_engine.shard_downloader.ensure_shard(shard))
+      asyncio.create_task(self.node.inference_engine.shard_downloader.ensure_shard(shard, self.inference_engine_classname))
 
       return web.json_response({
         "status": "success",

← 8c191050 download status in parallel, support async ensure shard with · back to Exo · Fix the /v1/models API to output proper OpenAI compatible en 627bfcae →