{"record":{"id":"eae290ca807fba18","repo":"sgl-project/sglang","slug":"image-qkv-shapes-must-match","errorCode":null,"errorMessage":"image QKV shapes must match","messagePattern":"image QKV shapes must match","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"python/sglang/kernels/ops/diffusion/rope/hunyuan_qkv_pack_triton.py","lineNumber":173,"sourceCode":"    txt_q: torch.Tensor,\n    txt_k: torch.Tensor,\n    txt_v: torch.Tensor,\n    cos: torch.Tensor,\n    sin: torch.Tensor,\n) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:\n    tensors = (img_q, img_k, img_v, txt_q, txt_k, txt_v)\n    if any(x.ndim != 4 for x in tensors):\n        raise ValueError(\"QKV tensors must have shape [B, S, H, D]\")\n    if any(not x.is_cuda or x.dtype != torch.bfloat16 for x in tensors):\n        raise ValueError(\"QKV tensors must be CUDA bfloat16 tensors\")\n    if any(x.device != img_q.device for x in tensors):\n        raise ValueError(\"QKV tensors must be on the same CUDA device\")\n    batch, img_tokens, num_heads, head_dim = img_q.shape\n    txt_tokens = txt_q.shape[1]\n    expected_img = (batch, img_tokens, num_heads, head_dim)\n    expected_txt = (batch, txt_tokens, num_heads, head_dim)\n    if any(tuple(x.shape) != expected_img for x in (img_q, img_k, img_v)):\n        raise ValueError(\"image QKV shapes must match\")\n    if any(tuple(x.shape) != expected_txt for x in (txt_q, txt_k, txt_v)):\n        raise ValueError(\"text QKV shapes must match\")\n    if any(x.stride(-1) != 1 for x in tensors):\n        raise ValueError(\"QKV last dimensions must be contiguous\")\n    if head_dim <= 0 or head_dim > 128 or head_dim % 2:\n        raise ValueError(\"head_dim must be positive, even, and <= 128\")\n    if cos.ndim != 2 or sin.ndim != 2 or cos.shape != sin.shape:\n        raise ValueError(\"cos and sin must have matching [S, D/2] shapes\")\n    if cos.shape[0] < img_tokens or cos.shape[1] != head_dim // 2:\n        raise ValueError(\"cos/sin shape does not cover image tokens and head_dim\")\n    if not cos.is_cuda or not sin.is_cuda or cos.stride(-1) != 1 or sin.stride(-1) != 1:\n        raise ValueError(\"cos and sin must be CUDA and last-dim contiguous\")\n    if cos.device != img_q.device or sin.device != img_q.device:\n        raise ValueError(\"QKV and cos/sin tensors must be on the same CUDA device\")\n\n    total_tokens = img_tokens + txt_tokens\n    storage = torch.empty(\n        (3, batch, total_tokens, num_heads, head_dim),","sourceCodeStart":155,"sourceCodeEnd":191,"githubUrl":"https://github.com/sgl-project/sglang/blob/0132848349585cfe6aae51c4941cbae872505f8a/python/sglang/kernels/ops/diffusion/rope/hunyuan_qkv_pack_triton.py#L155-L191","documentation":"img_q, img_k, img_v must share the exact same (B, img_tokens, num_heads, head_dim) shape, taken from img_q, since the kernel packs them into one interleaved buffer.","triggerScenarios":"Any of img_k or img_v having a different token count, head count, or head dim than img_q (e.g. GQA where kv heads weren't expanded to match, or mismatched sequence lengths after a split).","commonSituations":"Using grouped-query/MLA attention without repeating K/V heads to match Q heads before the fused pack; img tensor split at wrong boundaries.","solutions":["Repeat/expand K/V heads to match Q heads (e.g. torch.repeat_interleave on the head dim)","Ensure img_q/k/v come from chunking the same projection with consistent shapes"],"exampleFix":"# before\nimg_k = img_k  # (B, S, H_kv, D) with H_kv < H\n# after\nimg_k = img_k.repeat_interleave(H // H_kv, dim=2)  # (B, S, H, D)","handlingStrategy":"validation","validationCode":"expected = tuple(img_q.shape)\nassert all(tuple(t.shape) == expected for t in (img_k, img_v))","typeGuard":"def img_qkv_match(q, k, v) -> bool:\n    return q.shape == k.shape == v.shape","tryCatchPattern":null,"preventionTips":["Expand GQA kv heads to q heads before fused packing","Chunk projections so q/k/v inherit identical shapes"],"tags":["shape","attention","gqa","hunyuan","rope"],"backgroundTag":"tensor-shape-mismatch","analyzedSha":"0132848349585cfe6aae51c4941cbae872505f8a","analyzedAt":"2026-08-28T05:10:05.995Z","schemaVersion":2},"datasetVersion":"2026-08-28T06:17:29.519Z"}