owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

make minimal changes

Browse Source
This commit is contained in:
velaraptor-runpod
2026-02-13 03:23:44 -06:00
parent fefdbe21a9
commit 767c66c301
4 changed files with 89 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.runpod/hub.json
+17 -127
View File
@@ -509,34 +509,13 @@
"type": "string",
"description": "Speculative decoding method to use.",
"options": [
{
"label": "None",
"value": ""
},
{
"label": "Draft Model",
"value": "draft_model"
},
{
"label": "N-gram",
"value": "ngram"
},
{
"label": "EAGLE",
"value": "eagle"
},
{
"label": "EAGLE3",
"value": "eagle3"
},
{
"label": "Medusa",
"value": "medusa"
},
{
"label": "MLP Speculator",
"value": "mlp_speculator"
}
{ "label": "None", "value": "" },
{ "label": "Draft Model", "value": "draft_model" },
{ "label": "N-gram", "value": "ngram" },
{ "label": "EAGLE", "value": "eagle" },
{ "label": "EAGLE3", "value": "eagle3" },
{ "label": "Medusa", "value": "medusa" },
{ "label": "MLP Speculator", "value": "mlp_speculator" }
],
"default": "",
"advanced": true
@@ -578,6 +557,16 @@
"advanced": true
}
},
{
"key": "ENABLE_LOG_REQUESTS",
"input": {
"name": "Enable Log Requests",
"type": "boolean",
"description": "Enable vLLM request logging.",
"default": false,
"advanced": true
}
},
{
"key": "TOKENIZER_NAME",
"input": {
@@ -655,35 +644,6 @@
"advanced": true
}
},
{
"key": "ATTENTION_BACKEND",
"input": {
"name": "Attention Backend",
"type": "string",
"description": "Attention backend to use (e.g., FLASH_ATTN, XFORMERS, FLASHINFER).",
"advanced": true
}
},
{
"key": "ASYNC_SCHEDULING",
"input": {
"name": "Async Scheduling",
"type": "boolean",
"description": "Enable async scheduling for improved throughput.",
"default": false,
"advanced": true
}
},
{
"key": "STREAM_INTERVAL",
"input": {
"name": "Stream Interval",
"type": "number",
"description": "Interval in seconds between streaming responses.",
"default": 1,
"advanced": true
}
},
{
"key": "DEFAULT_BATCH_SIZE",
"input": {
@@ -844,76 +804,6 @@
"default": "",
"advanced": true
}
},
{
"key": "TRUST_REQUEST_CHAT_TEMPLATE",
"input": {
"name": "Trust Request Chat Template",
"type": "boolean",
"description": "Allow chat templates from incoming requests to override the server default.",
"default": false,
"advanced": true
}
},
{
"key": "RETURN_TOKENS_AS_TOKEN_IDS",
"input": {
"name": "Return Tokens as Token IDs",
"type": "boolean",
"description": "Return token IDs instead of token strings in responses.",
"default": false,
"advanced": true
}
},
{
"key": "EXCLUDE_TOOLS_WHEN_TOOL_CHOICE_NONE",
"input": {
"name": "Exclude Tools When Tool Choice None",
"type": "boolean",
"description": "When tool_choice is 'none', exclude tool definitions from the prompt.",
"default": false,
"advanced": true
}
},
{
"key": "ENABLE_PROMPT_TOKENS_DETAILS",
"input": {
"name": "Enable Prompt Tokens Details",
"type": "boolean",
"description": "Enable detailed prompt token usage in responses.",
"default": false,
"advanced": true
}
},
{
"key": "ENABLE_FORCE_INCLUDE_USAGE",
"input": {
"name": "Enable Force Include Usage",
"type": "boolean",
"description": "Force include usage information in all streaming responses.",
"default": false,
"advanced": true
}
},
{
"key": "ENABLE_LOG_OUTPUTS",
"input": {
"name": "Enable Log Outputs",
"type": "boolean",
"description": "Log model outputs for debugging.",
"default": false,
"advanced": true
}
},
{
"key": "LOG_ERROR_STACK",
"input": {
"name": "Log Error Stack",
"type": "boolean",
"description": "Log full error stack traces.",
"default": false,
"advanced": true
}
}
]
}