{"record":{"id":"df7edcae540f008d","repo":"sgl-project/sglang","slug":"b-must-be-2d-got-b-ndim-b-ndim","errorCode":null,"errorMessage":"`b` must be 2D (got b.ndim={b.ndim}).","messagePattern":"`b` must be 2D \\(got b\\.ndim=(.+?)\\)\\.","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"python/sglang/kernels/ops/attention/fla/fused_recurrent_linear_replayssm.py","lineNumber":482,"sourceCode":"        ``dt_bias``=[HV, K], ``g_cache``=[num_slots, HV, L, K].\n    ``A_log`` is [HV] (per-head scalar) for both.\n\n    Same call surface as the packed decode plus the three ring caches\n    (``d_cache`` / ``k_cache`` / ``g_cache``) and the per-decode-row\n    ``write_pos`` cursor.  ``initial_state`` is both the checkpoint read (h0)\n    and the (flush-only) checkpoint write (ht), in place.\n\n    Allocates nothing persistent: the caller owns the ring tensors and is\n    responsible for advancing / resetting ``write_pos`` (e.g. ``(write_pos+1) %\n    L`` after each step).  This is a STANDALONE kernel; the memory-pool / cache\n    integration is a later phase.\n    \"\"\"\n    if mixed_qkv.ndim != 2:\n        raise ValueError(f\"`mixed_qkv` must be 2D (got ndim={mixed_qkv.ndim}).\")\n    if mixed_qkv.stride(-1) != 1:\n        raise ValueError(\"`mixed_qkv` must be contiguous in the last dim.\")\n    if b.ndim != 2:\n        raise ValueError(f\"`b` must be 2D (got b.ndim={b.ndim}).\")\n    if A_log.ndim != 1:\n        raise ValueError(\"`A_log` must be a 1D tensor.\")\n    if initial_state.ndim != 4:\n        raise ValueError(f\"`initial_state` must be 4D (got ndim={initial_state.ndim}).\")\n    if not out.is_contiguous():\n        raise ValueError(\"`out` must be contiguous.\")\n    if write_pos.ndim != 1 or write_pos.dtype != torch.int32:\n        raise ValueError(\"`write_pos` must be a 1D int32 tensor.\")\n    if force_flush is not None and (\n        force_flush.ndim != 1 or force_flush.dtype != torch.int32\n    ):\n        raise ValueError(\"`force_flush` must be a 1D int32 tensor or None.\")\n\n    B = mixed_qkv.shape[0]\n    num_state_slots, HV, V, K = initial_state.shape\n    qkv_dim = mixed_qkv.shape[1]\n    q_dim = (qkv_dim - HV * V) // 2\n    if q_dim <= 0 or q_dim % K != 0:","sourceCodeStart":464,"sourceCodeEnd":500,"githubUrl":"https://github.com/sgl-project/sglang/blob/0132848349585cfe6aae51c4941cbae872505f8a/python/sglang/kernels/ops/attention/fla/fused_recurrent_linear_replayssm.py#L464-L500","documentation":"The gate logit b for replaySSM decode must be 2D [num_tokens, HV]: one row of gate logits per token. Passing 1D (per-head only) or 3D tensors fails this precondition.","triggerScenarios":"Passing b shaped [HV] (a single head-vector), [B, T, HV], or a transposed tensor to fused_recurrent_linear_replayssm_decode.","commonSituations":"Sharing a cached per-head b/a bias tensor across tokens; reshaping mismatches after switching from a chunked to decode API.","solutions":["Broadcast/reshape b to [num_tokens, HV] (e.g. b.expand(T, HV) if constant per token, or b.reshape(-1, HV))","Make sure num_tokens matches mixed_qkv.shape[0]"],"exampleFix":"// before\nb = a_log[None]  # or per-head [HV]\n// after\nb = b_1d.unsqueeze(0).expand(num_tokens, HV).contiguous()  # [T, HV]","handlingStrategy":"validation","validationCode":"assert b.ndim == 2 and b.shape[0] == mixed_qkv.shape[0]","typeGuard":null,"tryCatchPattern":null,"preventionTips":["Keep gate logits materialized per token [T, HV]","Share one tensor-shape validation helper for all replaySSM args"],"tags":["pytorch","tensor-shape","replayssm","gate"],"backgroundTag":"tensor-shape-mismatch","analyzedSha":"0132848349585cfe6aae51c4941cbae872505f8a","analyzedAt":"2026-08-28T05:10:05.995Z","schemaVersion":2},"datasetVersion":"2026-08-28T06:17:29.519Z"}