This commit is contained in:
2026-03-29 05:09:37 +08:00
parent 617665c6ab
commit 3e82fdb70e
4 changed files with 44 additions and 6 deletions
+6 -1
View File
@@ -1,12 +1,17 @@
MODEL_NAME=Qwen/Qwen3-14B
MODEL_CONFIG_FILE=config.json
MODEL_KEY=Qwen3.5-35B-A3B-GPTQ-Int4
MODEL_NAME=
HOST=0.0.0.0
PORT=8000
TENSOR_PARALLEL_SIZE=2
GPU_MEMORY_UTILIZATION=0.92
MAX_MODEL_LEN=8192
MAX_NUM_SEQS=64
MAX_TOKENS=4096
DTYPE=bfloat16
ENFORCE_EAGER=false
TRUST_REMOTE_CODE=false
TOOL_CALL_PARSER=
ENABLE_AUTO_TOOL_CHOICE=false
REVISION=
API_KEY=