Параметры

MODEL_NAME=huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated

MAX_MODEL_LEN=200000
DTYPE=auto
KV_CACHE_DTYPE=fp8
GPU_MEMORY_UTILIZATION=0.95
ENABLE_CHUNKED_PREFILL=true
ENABLE_PREFIX_CACHING=true
MAX_NUM_SEQS=4
MAX_CONCURRENCY=4
ENABLE_AUTO_TOOL_CHOICE=true
TOOL_CALL_PARSER=qwen3_xml
TRUST_REMOTE_CODE=false
LOAD_FORMAT=auto
PIPELINE_PARALLEL_SIZE=1
TENSOR_PARALLEL_SIZE=1
ENFORCE_EAGER=false
QUANTIZATION=None