Closed
[Bug-Report|缺陷反馈]: aclnnRmsNormQuant scale 维度与长度校验缺失(scale=[1,1]、[3] 均被放行,且长度>1 时只取 scale[0]) #7401
liuhanwen8Add on  26 days agoClosed at  17 days ago
liuhanwen8
liuhanwen8
26 days ago Create

现象

资料要求 scale 维度为 1、A2 产品下 shape 为 [1]。实测 scale=[1,1] 与 scale=[3] 两种非法形态第一段、第二段都返回 0;scale=[3] 且元素取 0.01/0.02/0.05 时,输出与 scale=[0.01] 的对照逐元素完全相同,说明只用第一个元素,其余被静默忽略。

场景 scale shape 第一段 第二段 输出 y[0..7]
合法基线 [1] 0 0 -73 -73 -73 -73 -73 -73 -73 -73
维度非法 [1,1] 0 0 -73 -73 -73 -73 -73 -73 -73 -73

期望

资料 norm/rms_norm_quant/docs/aclnnRmsNormQuant.md:scale 使用说明「维度为 1,长度要求见下方产品说明」;A2 段写明「scale 的 shape 为 [1]」。两种形态都应在第一段返回 161002。

环境

  • 硬件:Atlas A2 训练系列产品(Ascend 910B2,单卡复现)
  • CANN:9.2.0(Ascend-cann-toolkit_9.2.0_linux-aarch64)
  • 仓库:cann/ops-nn @ 711a4f5dda0d(norm/rms_norm_quant),2026-10-26

复现步骤

  1. 把下面「复现脚本」保存为 repro.cpp;
  2. 编译:
g++ -O2 -std=c++17 repro.cpp -o repro -I$ASCEND_HOME_PATH/include \
    -L$ASCEND_HOME_PATH/lib64 -lascendcl -lnnopbase -lopapi
  1. 运行对照:./repro ctrl 0、./repro scale2d 0;
  2. 读两行返回码(第一段 GetWorkspaceSize 与第二段 RmsNormQuant)。

复现脚本

#include <cstdio>
#include <cstdlib>
#include <string>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_rms_norm_quant.h"

static void* MkDev(size_t bytes) { void* p = nullptr; aclrtMalloc(&p, bytes, ACL_MEM_MALLOC_HUGE_FIRST); return p; }

static aclTensor* MkTen(const std::vector<int64_t>& sh, aclDataType dt, void* dev, size_t esz) {
  int64_t n = 1; for (auto v : sh) n *= v;
  std::vector<int64_t> st(sh.size(), 1);
  for (int i = (int)sh.size() - 2; i >= 0; --i) st[i] = sh[i + 1] * st[i + 1];
  return aclCreateTensor(sh.data(), sh.size(), dt, st.data(), 0, ACL_FORMAT_ND, sh.data(), sh.size(), dev);
}

int main(int argc, char** argv) {
  std::string sc = argc > 1 ? argv[1] : "ctrl";
  std::vector<int64_t> xs{3,5}, gs{1,5}, bs{1,5}, ss{1}, os{1}, ys{3,5};
  aclDataType ydt = ACL_INT8;
  if (sc == "gamma2d") gs = {3,5};
  else if (sc == "scale2d") { ss = {1,1}; os = {1,1}; }
  else if (sc == "scalelen3") { ss = {3}; os = {3}; }
  else if (sc == "empty") { xs = {0,5}; ys = {0,5}; }
  else if (sc == "yint4") { xs = {3,16}; gs = {1,16}; bs = {1,16}; ys = {3,16}; ydt = ACL_INT4; }
  else if (sc == "yint32") { xs = {3,40}; gs = {1,40}; bs = {1,40}; ys = {3,5}; ydt = ACL_INT32; }
  else if (sc == "xyrank3") { xs = {1,3,5}; ys = {3,5}; }
  if (aclInit(nullptr) != ACL_SUCCESS) return 1;
  if (aclrtSetDevice(atoi(argc > 2 ? argv[2] : "0")) != ACL_SUCCESS) return 1;
  aclrtStream stm = nullptr; aclrtCreateStream(&stm);
  auto num = [](const std::vector<int64_t>& s) { int64_t n = 1; for (auto v : s) n *= v; return (int)(n > 0 ? n : 1); };
  int nx = num(xs), ng = num(gs), nb = num(bs), ns = num(ss), no = num(os), ny = num(ys);
  std::vector<uint16_t> xh(nx), gh(ng), bh(nb), sh(ns);
  for (auto& v : xh) v = aclFloatToFloat16(-1.5f);
  for (auto& v : gh) v = aclFloatToFloat16(1.0f);
  for (auto& v : bh) v = aclFloatToFloat16(0.25f);
  for (int i = 0; i < ns; ++i) sh[i] = aclFloatToFloat16(sc == "scalelen3" ? std::vector<float>{0.01f,0.02f,0.05f}[i] : 0.01f);
  std::vector<int8_t> oh(no, 2), yh(ny * (ydt == ACL_INT4 ? 1 : 4), 0);
  void *dx = MkDev(nx*2), *dg = MkDev(ng*2), *db = MkDev(nb*2), *ds = MkDev(ns*2), *dof = MkDev(no), *dy = MkDev(yh.size());
  aclrtMemcpy(dx, nx*2, xh.data(), nx*2, ACL_MEMCPY_HOST_TO_DEVICE);
  aclrtMemcpy(dg, ng*2, gh.data(), ng*2, ACL_MEMCPY_HOST_TO_DEVICE);
  aclrtMemcpy(db, nb*2, bh.data(), nb*2, ACL_MEMCPY_HOST_TO_DEVICE);
  aclrtMemcpy(ds, ns*2, sh.data(), ns*2, ACL_MEMCPY_HOST_TO_DEVICE);
  aclrtMemcpy(dof, no, oh.data(), no, ACL_MEMCPY_HOST_TO_DEVICE);
  aclTensor* x = MkTen(xs, ACL_FLOAT16, dx, 2); aclTensor* g = MkTen(gs, ACL_FLOAT16, dg, 2);
  aclTensor* b = MkTen(bs, ACL_FLOAT16, db, 2); aclTensor* s = MkTen(ss, ACL_FLOAT16, ds, 2);
  aclTensor* o = MkTen(os, ACL_INT8, dof, 1);  aclTensor* y = MkTen(ys, ydt, dy, 1);
  uint64_t ws = 0; aclOpExecutor* ex = nullptr;
  auto r1 = aclnnRmsNormQuantGetWorkspaceSize(x, g, b, s, o, 1e-6, y, &ws, &ex);
  printf("[%s] GetWorkspaceSize = %d\n", sc.c_str(), (int)r1);
  if (r1 == 0) {
    void* p = ws > 0 ? MkDev((size_t)ws) : nullptr;
    auto r2 = aclnnRmsNormQuant(p, ws, ex, stm);
    printf("[%s] RmsNormQuant = %d\n", sc.c_str(), (int)r2);
    if (r2 == 0) {
      aclrtSynchronizeStream(stm);
      std::vector<int8_t> out(ny, 0);
      aclrtMemcpy(out.data(), ny, dy, ny, ACL_MEMCPY_DEVICE_TO_HOST);
      printf("  y[0..7]="); for (int i = 0; i < ny && i < 8; ++i) printf("%d ", out[i]); printf("\n");
    }
    if (p) aclrtFree(p);
  }
  aclFinalize();
  return 0;
}

实测输出:

[ctrl] GetWorkspaceSize = 0
[ctrl] RmsNormQuant = 0
[scale2d] GetWorkspaceSize = 0
[scale2d] RmsNormQuant = 0
  y[0..7]=-73 -73 -73 -73 -73 -73 -73 -73 
[scalelen3] GetWorkspaceSize = 0
[scalelen3] RmsNormQuant = 0
  y[0..7]=-73 -73 -73 -73 -73 -73 -73 -73 

影响

把 per-channel scale(长度=H)误传给 per-tensor 接口时不会报错,只会拿第一个通道的 scale 得到全表错误结果,且两段都返回 0 —— 静默错值比报错更难定位。规避方式:调用方自行断言 scale.numel()==1。

建议

aclnn_rms_norm_quant.cpp 的 CheckShapeDim:if (scaleDimNum != 1) 只打 OP_LOGE,随后 if (IsRegbase()) return false; 使非 regbase 路径只记日志不报错;另外全文没有 scale.numel() == 1 的检查,唯一的长度约束来自 OP_CHECK_SHAPE_NOT_EQUAL(scale, offset)。建议去掉 regbase 条件、并显式校验 scale/offset 元素数为 1,命中返回 161002。

likedislike
liuhanwen8liuhanwen8
26 days ago Added label: bug-report
yuning_chen
yuning_chenCollaborators
26 days ago Comments:

初步分析

感谢反馈,我们已开始核对这个问题。

现象理解:缺陷反馈;aclnnRmsNormQuant scale 维度与长度校验缺失(scale= 、 均被放行,且长度>1 时只取 scale )。
当前判断:从描述看,这是缺陷反馈「aclnnRmsNormQuant scale 维度与长度校验缺失(scale= 、 均被放行,且长度>1 时只取 scale )」(正文涉及返回码 161002)。正文已给出对照用例与期望/实际差异,更像参数校验、错误码语义或静默错值类问题。以上为初步判断,待复现确认,不能当成已确认根因。
涉及范围:aclnnRmsNormQuant、aclnnop、aclnn_rms_norm_quant
下一步:我们会对照资料契约与实现路径继续定位,并按需补充回归用例。

likedislike
yuning_chenyuning_chenCollaborators
25 days ago Assign liujie12345678 as responsible person
yuning_chen
yuning_chenCollaborators
25 days ago Comments:

您好,问题已收到,当前 @liujie12345678 正在处理中。

likedislike
liujie12345678liujie12345678Collaborators
25 days ago Assign liuyun_nj as responsible person
liujie12345678liujie12345678Collaborators
25 days ago Removed responsible person liujie12345678
liuyun_njliuyun_njCollaborators
17 days ago changed custom state from 进行中 to 已完成
liuyun_njliuyun_njCollaborators
17 days ago Close issue