[ROCm] Remove MRV1 model exceptions (#56360)

Signed-off-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Nick Hill
2026-10-10 05:09:19 +00:00
committed by GitHub
parent 8ea646b827
commit 7d0b4e57aa
2 changed files with 2 additions and 95 deletions
-30
View File
@@ -71,12 +71,6 @@ else:
logger = init_logger(__name__)
# TODO(rocm): These models are either unsupported by MRV2 or slower with
# MRV2 on AMD GPUs.
ROCM_DEFAULT_MRV1_ARCHITECTURES = frozenset(
{"DeepseekV32ForCausalLM", "DeepseekV4ForCausalLM", "GlmMoeDsaForCausalLM"}
)
DEFAULT_BREAKABLE_CUDAGRAPH_ARCHITECTURES = frozenset(
{
"DeepseekV32MTPModel",
@@ -727,30 +721,6 @@ class VllmConfig:
if use_v2_model_runner is not None:
return use_v2_model_runner
from vllm.platforms import current_platform
model_config = self.model_config
if model_config is not None and current_platform.is_rocm():
architectures = getattr(model_config, "architectures", ())
if any(arch in ROCM_DEFAULT_MRV1_ARCHITECTURES for arch in architectures):
# This default is a speed preference, not a claim that V1 can
# serve the config, so it yields where V1 cannot. It yields by
# falling through to the checks below, not by selecting V2.
v1_unsupported = self._get_v1_model_runner_unsupported_features()
if not v1_unsupported:
logger.warning_once(
"Defaulting to V1 model runner on ROCm for model "
"architectures: %s",
", ".join(architectures),
)
return False
logger.warning_once(
"Skipping the ROCm V1 model runner default for %s: V1 does "
"not support %s.",
", ".join(architectures),
", ".join(v1_unsupported),
)
if not HAS_TRITON:
logger.warning_once(
"Model Runner V2 requires Triton; using the V1 model runner instead."