|
|
@@ -37,6 +37,8 @@ pipeline_parallel_size = 1
|
|
|
distributed_backend = "mp"
|
|
|
args = [
|
|
|
"--served-model-name", "inclusionAI/Ling-3.1-flash",
|
|
|
+ "--enable-auto-tool-choice",
|
|
|
+ "--tool-call-parser", "ling3",
|
|
|
"--trust-remote-code",
|
|
|
"--max-model-len", "65536",
|
|
|
"--gpu-memory-utilization", "0.78",
|
