fix: update vllm serve comment to --runner pooling
Browse files
router.py
CHANGED
|
@@ -12,7 +12,7 @@ Usage:
|
|
| 12 |
result = router.route_text("What is the capital of France?")
|
| 13 |
|
| 14 |
# Option B: Remote vLLM server (no local GPU needed for embedding)
|
| 15 |
-
# Start server: vllm serve Qwen/Qwen3-0.6B --
|
| 16 |
router = R2Router.from_pretrained(path, embed_url="http://localhost:8000")
|
| 17 |
result = router.route_text("What is the capital of France?")
|
| 18 |
|
|
|
|
| 12 |
result = router.route_text("What is the capital of France?")
|
| 13 |
|
| 14 |
# Option B: Remote vLLM server (no local GPU needed for embedding)
|
| 15 |
+
# Start server: vllm serve Qwen/Qwen3-0.6B --runner pooling
|
| 16 |
router = R2Router.from_pretrained(path, embed_url="http://localhost:8000")
|
| 17 |
result = router.route_text("What is the capital of France?")
|
| 18 |
|