[Feature] Support batch invariance on ROCm (#52231)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com> Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
Andreas Karatzas
parent
50b21a2667
commit
e0317b28ce
@@ -288,6 +288,13 @@ def wvsplitkrc_dispatch(n: int, k: int, m: int, cu_count: int) -> tuple[int, boo
|
||||
def rocm_unquantized_gemm_impl(
|
||||
x: torch.Tensor, weight: torch.Tensor, bias: torch.Tensor | None = None
|
||||
) -> torch.Tensor:
|
||||
if envs.VLLM_BATCH_INVARIANT:
|
||||
from vllm.model_executor.determinism.batch_invariant import (
|
||||
linear_batch_invariant,
|
||||
)
|
||||
|
||||
return linear_batch_invariant(x, weight, bias)
|
||||
|
||||
from vllm.platforms.rocm import on_gfx1x, on_gfx9, on_gfx950, on_gfx1250
|
||||
|
||||
n = x.numel() // x.size(-1)
|
||||
|
||||
Reference in New Issue
Block a user