docs: mark EST_TOKENS optional in the env template
This commit is contained in:
+2
-2
@@ -8,11 +8,11 @@ LLM__QWEN__1__BASE_URL=
|
|||||||
LLM__QWEN__1__API_KEY=
|
LLM__QWEN__1__API_KEY=
|
||||||
LLM__QWEN__1__MODEL=
|
LLM__QWEN__1__MODEL=
|
||||||
LLM__QWEN__1__TIMEOUT_S=120
|
LLM__QWEN__1__TIMEOUT_S=120
|
||||||
# 可选(0 = 该闸不启用;TPM > 0 时 EST_TOKENS 必填 > 0):
|
# 可选(0 = 该闸不启用):
|
||||||
# LLM__QWEN__1__MAX_CONCURRENCY=8
|
# LLM__QWEN__1__MAX_CONCURRENCY=8
|
||||||
# LLM__QWEN__1__RPM=60
|
# LLM__QWEN__1__RPM=60
|
||||||
# LLM__QWEN__1__TPM=100000
|
# LLM__QWEN__1__TPM=100000
|
||||||
# LLM__QWEN__1__EST_TOKENS=2000
|
# LLM__QWEN__1__EST_TOKENS=2000 # 可选调优覆盖: TPM 入场预扣量;未填则库按 tpm//60 派生
|
||||||
# LLM__QWEN__1__TTFT_TIMEOUT_S=30 # 须与 INTER_TOKEN 成对;0 < inter < ttft < timeout
|
# LLM__QWEN__1__TTFT_TIMEOUT_S=30 # 须与 INTER_TOKEN 成对;0 < inter < ttft < timeout
|
||||||
# LLM__QWEN__1__INTER_TOKEN_TIMEOUT_S=15
|
# LLM__QWEN__1__INTER_TOKEN_TIMEOUT_S=15
|
||||||
# LLM__QWEN__1__ENABLE_THINKING=true # 三态: 缺省=不注入 / true=注入开启 / false=注入关闭
|
# LLM__QWEN__1__ENABLE_THINKING=true # 三态: 缺省=不注入 / true=注入开启 / false=注入关闭
|
||||||
|
|||||||
Reference in New Issue
Block a user