This commit is contained in:
2026-03-29 05:06:19 +08:00
parent 67eb27f2d2
commit 617665c6ab
12 changed files with 452 additions and 1 deletions
+12
View File
@@ -0,0 +1,12 @@
MODEL_NAME=Qwen/Qwen3-14B
HOST=0.0.0.0
PORT=8000
TENSOR_PARALLEL_SIZE=2
GPU_MEMORY_UTILIZATION=0.92
MAX_MODEL_LEN=8192
MAX_NUM_SEQS=64
DTYPE=bfloat16
ENFORCE_EAGER=false
TRUST_REMOTE_CODE=false
REVISION=
API_KEY=