[Fix] Environment variable SGL_* is deprecated (#14943)
This commit is contained in:
@@ -33,7 +33,7 @@ envs.SGLANG_IN_DEEPGEMM_PRECOMPILE_STAGE.set(True)
|
||||
# Force enable deep gemm
|
||||
envs.SGLANG_ENABLE_JIT_DEEPGEMM.set(True)
|
||||
# Force enable mha chunked kv for DeepSeek V3 to avoid missing kv_b_proj DeepGEMM case
|
||||
os.environ["SGL_CHUNKED_PREFIX_CACHE_THRESHOLD"] = "0"
|
||||
os.environ["SGLANG_CHUNKED_PREFIX_CACHE_THRESHOLD"] = "0"
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
|
||||
@@ -25,8 +25,8 @@ if ENABLE_JIT_DEEPGEMM:
|
||||
_BUILTIN_M_LIST = list(range(1, 1024 * 16 + 1))
|
||||
_ENABLE_JIT_DEEPGEMM_PRECOMPILE = envs.SGLANG_JIT_DEEPGEMM_PRECOMPILE.get()
|
||||
_DO_COMPILE_ALL = True
|
||||
_IS_FIRST_RANK_ON_NODE = get_bool_env_var("SGL_IS_FIRST_RANK_ON_NODE", "true")
|
||||
_IN_PRECOMPILE_STAGE = get_bool_env_var("SGL_IN_DEEPGEMM_PRECOMPILE_STAGE", "false")
|
||||
_IS_FIRST_RANK_ON_NODE = get_bool_env_var("SGLANG_IS_FIRST_RANK_ON_NODE", "true")
|
||||
_IN_PRECOMPILE_STAGE = get_bool_env_var("SGLANG_IN_DEEPGEMM_PRECOMPILE_STAGE", "false")
|
||||
|
||||
# Force redirect deep_gemm cache_dir
|
||||
os.environ["DG_JIT_CACHE_DIR"] = os.getenv(
|
||||
|
||||
@@ -1464,7 +1464,7 @@ class DeepseekV2AttentionMLA(nn.Module):
|
||||
|
||||
# TODO: Design a finer way to determine the threshold
|
||||
self.chunked_prefix_cache_threshold = get_int_env_var(
|
||||
"SGL_CHUNKED_PREFIX_CACHE_THRESHOLD", 8192
|
||||
"SGLANG_CHUNKED_PREFIX_CACHE_THRESHOLD", 8192
|
||||
)
|
||||
|
||||
# If we have self.fused_qkv_a_proj_with_mqa and we're running on CPU, we will choose the torch.ops.sgl_kernel.qkv_proj_with_rope_fused_weight kernel
|
||||
|
||||
Reference in New Issue
Block a user