[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)
This commit is contained in:
@@ -232,6 +232,9 @@ class Envs:
|
||||
SGLANG_ROCM_FUSED_DECODE_MLA = EnvBool(False)
|
||||
SGLANG_ROCM_DISABLE_LINEARQUANT = EnvBool(False)
|
||||
|
||||
# NPU
|
||||
SGLANG_NPU_DISABLE_ACL_FORMAT_WEIGHT = EnvBool(False)
|
||||
|
||||
# Quantization
|
||||
SGLANG_INT4_WEIGHT = EnvBool(False)
|
||||
SGLANG_CPU_QUANTIZATION = EnvBool(False)
|
||||
|
||||
Reference in New Issue
Block a user