[quant] fix fp32 downcasting (#19844)
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
This commit is contained in:
@@ -326,6 +326,7 @@ class Envs:
|
||||
SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN = EnvBool(False)
|
||||
SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2 = EnvBool(False)
|
||||
SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE = EnvBool(False)
|
||||
SGLANG_QUANT_ALLOW_DOWNCASTING = EnvBool(False)
|
||||
|
||||
# Flashinfer
|
||||
SGLANG_IS_FLASHINFER_AVAILABLE = EnvBool(True)
|
||||
|
||||
Reference in New Issue
Block a user