Hacktoberfest 2026：维护者为十月标记出来的 issue，仍然开放、适合新手。 浏览 Hacktoberfest issue

Qualcomm: 8-bit per-channel weight scales are floored at the 16-bit eps, and the HTP miscomputes near-zero channels

未关闭
  • 哪里不对？
#23,160 1 条评论 0 个 reaction 已指派 1 人 在 GitHub 查看

维护者通常 1 天内回复

@psiddh 已经在做这个了。

开始于 2026年9月25日。

评估

这个 Issue 还没有评估数据。

描述

module: qnn partner: qualcomm

get_ptq_per_channel_quant_config floors every per-channel weight scale at DEFAULT_EPS_16BIT (1.5e-9), 8-bit weights included. A conv output channel that BatchNorm has all but zeroed gets that scale, ~1e6x below its neighbours, and the HTP computes the channel as garbage. Host fake-quant is correct.

16a8w on SM8850 (Galaxy S26 Ultra, QAIRT 2.47), 200 VOC2012 val images, mIoU:

default eps eps=DEFAULT_EPS_8BIT XNNPACK int8
DeepLabV3-ResNet101 0.10% 78.90% 78.82%
FCN-ResNet101 28.69% 74.93% 74.99%

Repro, one conv. Writes both .pte files, the input and the fp32 reference to the directory given as the first argument:

import sys
import torch
from executorch.backends.qualcomm.export_utils import make_quantizer
from executorch.backends.qualcomm.quantizer.qconfig import DEFAULT_EPS_8BIT
from executorch.backends.qualcomm.quantizer.quantizer import QuantDtype
from executorch.backends.qualcomm.serialization.qc_schema import QcomChipset
from executorch.backends.qualcomm.utils.utils import (
    generate_htp_compiler_spec, generate_qnn_executorch_compiler_spec,
    get_qnn_context_binary_alignment, to_edge_transform_and_lower_to_qnn)
from executorch.exir.capture._config import ExecutorchBackendConfig
from executorch.exir.passes.memory_planning_pass import MemoryPlanningPass
from torchao.quantization.pt2e.quantize_pt2e import convert_pt2e, prepare_pt2e

torch.manual_seed(0)
conv = torch.nn.Conv2d(16, 16, 3, padding=1)
with torch.no_grad():
    conv.weight[0] *= 1e-8  # what BatchNorm with gamma ~ 0 leaves after folding
    conv.bias[0] = 0.0
model = torch.nn.Sequential(conv).eval()
calib = [torch.randn(1, 16, 32, 32) for _ in range(8)]
x = torch.randn(1, 16, 32, 32)
out = sys.argv[1]
x.numpy().tofile(f"{out}/input_0.raw")
with torch.no_grad():
    model(x).numpy().tofile(f"{out}/ref.raw")
for tag, eps in [("default", None), ("eps8bit", DEFAULT_EPS_8BIT)]:
    p = prepare_pt2e(torch.export.export(model, (x,)).module(),
                     make_quantizer(quant_dtype=QuantDtype.use_16a8w, soc_model="SM8850", eps=eps))
    for c in calib:
        p(c)
    q = convert_pt2e(p)
    spec = generate_qnn_executorch_compiler_spec(soc_model=QcomChipset.SM8850,
        backend_options=generate_htp_compiler_spec(use_fp16=False))
    prog = to_edge_transform_and_lower_to_qnn(q, (x,), spec).to_executorch(ExecutorchBackendConfig(
        memory_planning_pass=MemoryPlanningPass(alloc_graph_input=True, alloc_graph_output=True),
        segment_alignment=get_qnn_context_binary_alignment()))
    open(f"{out}/conv_dead_ch_{tag}.pte", "wb").write(prog.buffer)

Run each .pte with qnn_executor_runner on input_0.raw and read channel 0 of the output. It should be 0 (fp32 max 2.2e-8). With the default eps it comes out at 2.25; with eps=DEFAULT_EPS_8BIT it is 0.0. The other 15 channels match fp32 equally well in both runs (relative error 0.0069), and host fake-quant gives 0.0 in both cases.

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

主要语言
Python
星标
5k
派生
1.2k
平均合并
2 天 9 小时
30 天内合并 PR
555

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。