[ROCM] [FEAT] Integrate Aiter hipBLASLt GEMM online tuning (#40426)

Signed-off-by: hanlin12 <hanlin12@amd.com>
Signed-off-by: Han Lin <hanlin12@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
This commit is contained in:
Han Lin
2026-06-04 23:45:36 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> TJian
parent c505cd93ef
commit 165b7864d0
6 changed files with 591 additions and 0 deletions
+4
View File
@@ -115,6 +115,7 @@ if TYPE_CHECKING:
VLLM_ROCM_USE_AITER: bool = False
VLLM_ROCM_USE_AITER_PAGED_ATTN: bool = False
VLLM_ROCM_USE_AITER_LINEAR: bool = True
VLLM_ROCM_USE_AITER_LINEAR_HIPBMM: bool = False
VLLM_ROCM_USE_AITER_MOE: bool = True
VLLM_ROCM_AITER_MOE_DISPATCH_POLICY: int = 0
VLLM_ROCM_USE_AITER_RMSNORM: bool = True
@@ -1117,6 +1118,9 @@ environment_variables: dict[str, Callable[[], Any]] = {
"VLLM_ROCM_USE_AITER_LINEAR": lambda: (
os.getenv("VLLM_ROCM_USE_AITER_LINEAR", "True").lower() in ("true", "1")
),
"VLLM_ROCM_USE_AITER_LINEAR_HIPBMM": lambda: (
os.getenv("VLLM_ROCM_USE_AITER_LINEAR_HIPBMM", "False").lower() in ("true", "1")
),
# Whether to use aiter moe ops.
# By default is enabled.
"VLLM_ROCM_USE_AITER_MOE": lambda: (