Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
@@ -1 +1,3 @@
!*.png
!*.png
__pycache__/
*.pyc
11 changes: 11 additions & 0 deletions .runpod/hub.json
Original file line number Diff line number Diff line change
Expand Up @@ -323,6 +323,17 @@
"advanced": true
}
},
{
"key": "IS_EMBEDDING",
"input": {
"name": "Is Embedding Model",
"type": "boolean",
"description": "Set to true if using an embedding model",
"default": false,
"required": false,
"advanced": true
}
},
{
"key": "SKIP_TOKENIZER_INIT",
"input": {
Expand Down
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ All behaviour is controlled through environment variables:
| `FILE_STORAGE_PATH` | Directory for storing uploaded/generated files | "sglang_storage" | |
| `DATA_PARALLEL_SIZE` | Data parallelism size | 1 | |
| `LOAD_BALANCE_METHOD` | Load balancing strategy | "round_robin" | "round_robin", "shortest_queue" |
| `IS_EMBEDDING` | Set to true for embedding models | false | boolean (true or false) |
| `SKIP_TOKENIZER_INIT` | Skip tokenizer init | false | boolean (true or false) |
| `TRUST_REMOTE_CODE` | Allow custom models from Hub | false | boolean (true or false) |
| `LOG_REQUESTS` | Log inputs and outputs of requests | false | boolean (true or false) |
Expand Down
1 change: 1 addition & 0 deletions engine.py
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,7 @@ def start_server(self):

# Boolean flags
boolean_flags = [
"IS_EMBEDDING",
"SKIP_TOKENIZER_INIT",
"TRUST_REMOTE_CODE",
"LOG_REQUESTS",
Expand Down