Qualcomm AI Engine Direct: a delegated mutable buffer starts from leftover memory

未关闭
  • 哪里不对？
#24,749 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
48/100
Issue 类型
缺陷
描述清晰度
基本清楚
活跃度
活跃
技术栈
python
领域
embedded-iot, machine-learning

调研方向

Start by reading the QNN partitioner logic that decides whether mutable buffers are delegated, including the int64 special case, and trace how delegated buffers are initialized before their first run. Reproduce the counter example with the QNN SDK 2.51 x86 simulator and compare delegated results with CPU results. Done means delegated buffers begin with the registered value across dtypes, and the int64 special case can be removed.

由索引模型根据 Issue 内容生成。

描述

module: qnn partner: qualcomm

When the QNN partitioner delegates a mutable buffer (the default,
skip_mutable_buffer=False), the buffer lives in memory that the QNN delegate
owns. Nothing sets that memory before the first run, so the buffer starts from
whatever the memory held. The result is wrong with no error.

Example: a counter that should start at zero.

class Int32Counter(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.register_buffer("count", torch.zeros(2, dtype=torch.int32))

    def forward(self, x):
        self.count.add_(x.argmax(-1).to(torch.int32))
        return x * 2, self.count + 0

With x = [[0.1, 0.9, 0.2], [0.7, 0.1, 0.3]] the first run should return
count = [1, 0]. Lowered for HTP float16 and run on the QNN SDK 2.51 x86
simulator, it returns values like [-1486893823, 32716], different on every
run.

Int64 buffers already stay on CPU for this reason, and the same counter with
an int64 buffer comes out right. Buffers of other dtypes,
including float buffers such as KV caches, are still delegated.

Expected: a delegated buffer starts from the same value as a CPU one, so the
int64 special case in the partitioner can go.

cc @cccclai @winskuo-quic @shewu-quic @haowhsu-quic @DannyYuyang-quic @qti-horodnic @cbilgin @abhinaykukkadapu @psiddh

主要语言
Python
星标
5.2k
派生
1.2k
平均合并
1 天 23 小时
30 天内合并 PR
696

环境准备

从这里开始

  1. 先读完整个 Issue，再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库，在一个分支上完成修改。
  4. 提交 Pull Request，并在描述里引用这个 Issue 编号。

pytorch/executorch 的其他 Issue

查看 pytorch/executorch 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。