sglang/docs/platforms/ascend_npu_environment_variables.md

Environment Variables

SGLang supports various environment variables related to Ascend NPU that can be used to configure its runtime behavior. This document provides a list of commonly used environment variables and aims to stay updated over time.

Directly Used in SGLang

Environment Variable	Description	Default Value
SGLANG_NPU_USE_MLAPO	Adopts the MLAPO fusion operator in attention preprocessing stage of the MLA model.	false
SGLANG_USE_FIA_NZ	Reshapes KV Cache for FIA NZ format. SGLANG_USE_FIA_NZ must be enabled with SGLANG_NPU_USE_MLAPO	false
SGLANG_NPU_USE_MULTI_STREAM	Enable dual-stream computation of shared experts and routing experts in DeepSeek models. Enable dual-stream computation in DeepSeek NSA Indexer.	false
SGLANG_NPU_DISABLE_ACL_FORMAT_WEIGHT	Disable cast model weight tensor to a specific NPU ACL format.	false
SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK	The maximum number of dispatched tokens on each rank.	128

Used in DeepEP Ascend

Environment Variable	Description	Default Value
DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS	Enable ant-moving function in dispatch stage. Indicates the number of tokens transmitted per round on each rank.	8192
DEEPEP_NORMAL_LONG_SEQ_ROUND	Enable ant-moving function in dispatch stage. Indicates the number of rounds transmitted on each rank.	1
DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ	Enable ant-moving function in combine stage. The value 0 means disabled.	0
MOE_ENABLE_TOPK_NEG_ONE	Needs to be enabled when the expert ID to be processed by DEEPEP contains -1.	0
DEEP_NORMAL_MODE_USE_INT8_QUANT	Quantizes x to int8 and returns (tensor, scales) in dispatch operator.	0

Others

Environment Variable	Description	Default Value
TASK_QUEUE_ENABLE	Used to control the optimization level of the dispatch queue about the task_queue operator. Detail	1
INF_NAN_MODE_ENABLE	Controls whether the chip uses saturation mode or INF_NAN mode. Detail	1
STREAMS_PER_DEVICE	Configures the maximum number of streams for the stream pool. Detail	32
PYTORCH_NPU_ALLOC_CONF	Controls the behavior of the cache allocator. This variable changes memory usage and may cause performance fluctuations. Detail
ASCEND_MF_STORE_URL	The address of config store in MemFabric during PD separation, which is generally set to the IP address of the P primary node with an arbitrary port number.
ASCEND_LAUNCH_BLOCKING	Controls whether synchronous mode is enabled during operator execution. Detail	0
HCCL_OP_EXPANSION_MODE	Configures the expansion position for communication algorithm scheduling. Detail
HCCL_BUFFSIZE	Controls the size of the buffer area for shared data between two NPUs. The unit is MB, and the value must be greater than or equal to 1. Detail	200
HCCL_SOCKET_IFNAME	Configures the name of the network card used by the Host during HCCL initialization. Detail
GLOO_SOCKET_IFNAME	Configures the network interface name for GLOO communication.