mxfp4 recipes: --moe-backend flashinfer_cutlass (the Sept-tree CLI family; _afp8 was not a valid choice on r35 - first boot argparse)

recipes/glm53-full-mxfp4-4x-probe/recipe.toml

@@ -206,7 +206,13 @@ args = [
     # MoE backend from the log. WHICHEVER backend runs, validate the numerics:
     # the missing-SwiGLU-clamp class of bug (r33/r34: runaway generation) and
     # the W4A4 token-loop corruption both show up as degenerate repeats.
-    "--moe-backend", "flashinfer_cutlass_afp8",
+    # (The lab runbook's literal `flashinfer_cutlass_afp8` was a CLI choice in
+    #  their June tree. The Sept tree's CLI coarsens it to the `flashinfer_cutlass`
+    #  family, which the oracle (fused_moe/oracle/mxfp4.py) maps to
+    #  [FLASHINFER_CUTLASS_MXFP4_BF16, FLASHINFER_CUTLASS_MXFP4_MXFP8] with the
+    #  `_afp8` activation key resolving the MXFP8 kernel. The exact string is
+    #  rejected by argparse on r35 — verified on the first boot attempt.)
+    "--moe-backend", "flashinfer_cutlass",
     # pure I/O loader (kept across every GLM config)
     "--load-format", "instanttensor",
     "--block-size", "256",

recipes/glm53-full-mxfp4-4x/recipe.toml

@@ -201,7 +201,13 @@ args = [
     # MoE backend from the log. WHICHEVER backend runs, validate the numerics:
     # the missing-SwiGLU-clamp class of bug (r33/r34: runaway generation) and
     # the W4A4 token-loop corruption both show up as degenerate repeats.
-    "--moe-backend", "flashinfer_cutlass_afp8",
+    # (The lab runbook's literal `flashinfer_cutlass_afp8` was a CLI choice in
+    #  their June tree. The Sept tree's CLI coarsens it to the `flashinfer_cutlass`
+    #  family, which the oracle (fused_moe/oracle/mxfp4.py) maps to
+    #  [FLASHINFER_CUTLASS_MXFP4_BF16, FLASHINFER_CUTLASS_MXFP4_MXFP8] with the
+    #  `_afp8` activation key resolving the MXFP8 kernel. The exact string is
+    #  rejected by argparse on r35 — verified on the first boot attempt.)
+    "--moe-backend", "flashinfer_cutlass",
     # pure I/O loader (kept across every GLM config)
     "--load-format", "instanttensor",
     "--block-size", "256",