[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)

Signed-off-by: maral <maralbahari.98@gmail.com> Signed-off-by: Maral <maralbahari.98@gmail.com>
2026-04-09 08:50:39 +08:00
parent 8332078cfd
commit 2e9034c998
35 changed files with 1710 additions and 904 deletions
--- a/tests/compile/passes/distributed/test_sequence_parallelism.py
+++ b/tests/compile/passes/distributed/test_sequence_parallelism.py
@@ -109,6 +109,7 @@ class TestAllReduceRMSNormStaticQuantFP8Model(torch.nn.Module):
                weight_shape=(hidden_size, hidden_size),
                activation_quant_key=self.quant_key,
                weight_quant_key=self.quant_key,
+                input_dtype=self.vllm_config.model_config.dtype,
            )
            for i in range(3)
        ]