|
|
@@ -21,14 +21,12 @@ args = [
|
|
|
"--max-num-batched-tokens", "8192",
|
|
|
"--gpu-memory-utilization", "0.82",
|
|
|
"--enable-prefix-caching",
|
|
|
- "--speculative-config", """
|
|
|
-'{"method":"mtp","num_speculative_tokens":2}'""",
|
|
|
+ "--speculative-config", '{"method":"mtp","num_speculative_tokens":2}',
|
|
|
"--tokenizer-mode", "deepseek_v4",
|
|
|
"--tool-call-parser", "deepseek_v4",
|
|
|
"--enable-auto-tool-choice",
|
|
|
"--reasoning-parser", "deepseek_v4",
|
|
|
- "--reasoning-config", """
|
|
|
-'{"reasoning_parser":"deepseek_v4","reasoning_start_str":"","reasoning_end_str":""}'""",
|
|
|
+ "--reasoning-config", '{"reasoning_parser":"deepseek_v4","reasoning_start_str":"","reasoning_end_str":""}',
|
|
|
"--default-chat-template-kwargs.thinking", "true",
|
|
|
"--default-chat-template-kwargs.reasoning_effort", "high",
|
|
|
"--enable-flashinfer-autotune",
|