[ROCm] Disable AITER FP8/FP4 BMM for MLA by default (#53123)

Signed-off-by: xuebwang-amd <xuebwang@amd.com>
This commit is contained in:
xuebwang
2026-10-14 10:46:02 +00:00
committed by GitHub
parent c67c69e657
commit 81503550f3
4 changed files with 16 additions and 10 deletions
+9 -8
View File
@@ -153,8 +153,8 @@ if TYPE_CHECKING:
VLLM_ROCM_USE_AITER_FP4_ASM_GEMM: bool = False
VLLM_ROCM_USE_AITER_TRITON_SPARSE_MLA: bool = False
VLLM_ROCM_USE_AITER_TRITON_ROPE: bool = False
VLLM_ROCM_USE_AITER_FP8BMM: bool = True
VLLM_ROCM_USE_AITER_FP4BMM: bool = True
VLLM_ROCM_USE_AITER_FP8BMM: bool = False
VLLM_ROCM_USE_AITER_FP4BMM: bool = False
VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION: bool = False
VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS: bool = False
VLLM_ROCM_AITER_MEGA_MOE_FUSE_SHARED_EXPERTS: bool = False
@@ -1381,15 +1381,16 @@ environment_variables: dict[str, Callable[[], Any]] = {
"VLLM_ROCM_USE_AITER_TRITON_ROPE": lambda: (
os.getenv("VLLM_ROCM_USE_AITER_TRITON_ROPE", "False").lower() in ("true", "1")
),
# Whether to use aiter triton fp8 bmm kernel
# By default is enabled.
# Whether to use aiter triton fp8 bmm kernel for MLA kv_b_proj.
# By default is disabled: it re-quantizes the projection weights online,
# regardless of the precision the checkpoint asked for.
"VLLM_ROCM_USE_AITER_FP8BMM": lambda: (
os.getenv("VLLM_ROCM_USE_AITER_FP8BMM", "True").lower() in ("true", "1")
os.getenv("VLLM_ROCM_USE_AITER_FP8BMM", "False").lower() in ("true", "1")
),
# Whether to use aiter triton fp4 bmm kernel
# By default is enabled.
# Whether to use aiter triton fp4 bmm kernel for MLA kv_b_proj.
# By default is disabled, for the same reason as the fp8 variant above.
"VLLM_ROCM_USE_AITER_FP4BMM": lambda: (
os.getenv("VLLM_ROCM_USE_AITER_FP4BMM", "True").lower() in ("true", "1")
os.getenv("VLLM_ROCM_USE_AITER_FP4BMM", "False").lower() in ("true", "1")
),
# Use AITER triton unified attention for V1 attention
"VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION": lambda: (