{"record":{"id":"c06d9b8802227b94","repo":"sgl-project/sglang","slug":"o-tensor-must-have-3-or-4-dimensions-batch-seql","errorCode":null,"errorMessage":"O tensor must have 3 or 4 dimensions: (batch, seqlen, nheads, headdim) or (total_q, nheads, headdim)","messagePattern":"O tensor must have 3 or 4 dimensions: \\(batch, seqlen, nheads, headdim\\) or \\(total_q, nheads, headdim\\)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"python/sglang/kernels/ops/attention/flash_attn/cute/flash_fwd_combine.py","lineNumber":239,"sourceCode":"            raise TypeError(\"O partial tensor must match dtype_partial\")\n        if const_expr(not (mO.element_type == self.dtype)):\n            raise TypeError(\"O tensor must match dtype\")\n        if const_expr(mLSE_partial.element_type not in [Float32]):\n            raise TypeError(\"LSE partial tensor must be Float32\")\n        if const_expr(mLSE is not None and mLSE.element_type not in [Float32]):\n            raise TypeError(\"LSE tensor must be Float32\")\n\n        # Shape validation - input tensors are in user format, need to be converted to kernel format\n        if const_expr(len(mO_partial.shape) not in [4, 5]):\n            raise ValueError(\n                \"O partial tensor must have 4 or 5 dimensions: (num_splits, batch, seqlen, nheads, headdim) or (num_splits, total_q, nheads, headdim)\"\n            )\n        if const_expr(len(mLSE_partial.shape) not in [3, 4]):\n            raise ValueError(\n                \"LSE partial tensor must have 3 or 4 dimensions: (num_splits, batch, seqlen, nheads) or (num_splits, total_q, nheads)\"\n            )\n        if const_expr(len(mO.shape) not in [3, 4]):\n            raise ValueError(\n                \"O tensor must have 3 or 4 dimensions: (batch, seqlen, nheads, headdim) or (total_q, nheads, headdim)\"\n            )\n        if const_expr(mLSE is not None and len(mLSE.shape) not in [2, 3]):\n            raise ValueError(\n                \"LSE tensor must have 2 or 3 dimensions: (batch, seqlen, nheads) or (total_q, nheads)\"\n            )\n\n        mO_partial, mO = [assume_tensor_aligned(t) for t in (mO_partial, mO)]\n        # (num_splits, b, seqlen, h, d) -> (seqlen, d, num_splits, h, b)\n        # or (num_splits, total_q, h, d) -> (total_q, d, num_splits, h)\n        O_partial_layout_transpose = (\n            [2, 4, 0, 3, 1] if const_expr(cu_seqlens is None) else [1, 3, 0, 2]\n        )\n        # (b, seqlen, h, d) -> (seqlen, d, h, b) or (total_q, h, d) -> (total_q, d, h)\n        mO_partial = cute.make_tensor(\n            mO_partial.iterator,\n            cute.select(mO_partial.layout, mode=O_partial_layout_transpose),\n        )","sourceCodeStart":221,"sourceCodeEnd":257,"githubUrl":"https://github.com/sgl-project/sglang/blob/0132848349585cfe6aae51c4941cbae872505f8a/python/sglang/kernels/ops/attention/flash_attn/cute/flash_fwd_combine.py#L221-L257","documentation":"The final output tensor mO must be 3D (batch, seqlen, nheads, headdim) or 4D varlen (total_q, nheads, headdim) — i.e. one rank less than the partials, without the num_splits axis.","triggerScenarios":"Passing an mO that still contains the num_splits axis, or a 2D folded output.","commonSituations":"Reusing the partial tensor's shape when allocating the output buffer; forgetting the combine reduces over splits.","solutions":["Allocate mO without the leading num_splits dimension","For batched input use (b, s, h, d); for varlen use (total_q, h, d)"],"exampleFix":"// before\nmO = torch.empty(num_splits, b, s, h, d, dtype=dt)\n// after\nmO = torch.empty(b, s, h, d, dtype=dt)","handlingStrategy":"validation","validationCode":"assert mO.dim() in (3, 4) and mO.dim() == mO_partial.dim() - 1","typeGuard":"def final_o_ok(o, o_partial) -> bool:\n    return o.dim() in (3, 4) and o.dim() == o_partial.dim() - 1","tryCatchPattern":null,"preventionTips":["Allocate output as o_partial[0].new_empty(o_partial.shape[1:], ...) to inherit correct rank"],"tags":["flash-attention","shape-mismatch","validation"],"backgroundTag":"tensor-shape-mismatch","analyzedSha":"0132848349585cfe6aae51c4941cbae872505f8a","analyzedAt":"2026-08-28T05:10:05.995Z","schemaVersion":2},"datasetVersion":"2026-08-28T06:17:29.519Z"}