Merge branch 'main' into feat/update-vllm-v0.15.0
This commit is contained in:
@@ -645,16 +645,6 @@
|
||||
"advanced": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "MAX_SEQ_LEN_TO_CAPTURE",
|
||||
"input": {
|
||||
"name": "CUDA Graph Max Content Length",
|
||||
"type": "number",
|
||||
"description": "Maximum context length covered by CUDA graphs. If a sequence has context length larger than this, we fall back to eager mode",
|
||||
"default": 8192,
|
||||
"advanced": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "DISABLE_CUSTOM_ALL_REDUCE",
|
||||
"input": {
|
||||
@@ -792,16 +782,6 @@
|
||||
"advanced": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "ENABLE_LOG_REQUESTS",
|
||||
"input": {
|
||||
"name": "Enable Log Requests",
|
||||
"type": "boolean",
|
||||
"description": "Enables vLLM request logging",
|
||||
"default": false,
|
||||
"advanced": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "ENABLE_AUTO_TOOL_CHOICE",
|
||||
"input": {
|
||||
|
||||
Reference in New Issue
Block a user