QNN backend model convert cost many memory.

[enduringstack]

🐛 Describe the bug

according to this link: https://github.com/pytorch/executorch/blob/main/examples/demo-apps/android/LlamaDemo/docs/delegates/qualcomm_README.md

model convert: python3 -m examples.models.llama2.export_llama --checkpoint "${MODEL_DIR}/consolidated.00.pth" -p "${MODEL_DIR}/params.json" -kv --disable_dynamic_shape --qnn --pt2e_quantize qnn_16a4w -d fp32 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name="testchenllama3dot2_1B.pte"

model is llama3.2 1B， the convert process cost 30+GB memory and it's still incresing.....

Versions

Collecting environment information...
PyTorch version: N/A
Is debug build: N/A
CUDA used to build PyTorch: N/A
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04 LTS (x86_64)
GCC version: (Ubuntu 11.2.0-19ubuntu1) 11.2.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.35

Python version: 3.12.4 | packaged by Anaconda, Inc. | (main, Jun 18 2024, 15:12:24) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-25-generic-x86_64-with-glibc2.35
Is CUDA available: N/A
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: Could not collect
Nvidia driver version: Could not collect
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: N/A

CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 42 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 6278C CPU @ 2.60GHz
CPU family: 6
Model: 85
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
Stepping: 7
BogoMIPS: 5200.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 arat avx512_vnni md_clear flush_l1d arch_capabilities
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 256 KiB (8 instances)
L1i cache: 256 KiB (8 instances)
L2 cache: 8 MiB (8 instances)
L3 cache: 35.8 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Itlb multihit: KVM: Mitigation: VMX unsupported
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown

Versions of relevant libraries:
[pip3] flake8==7.0.0
[pip3] mypy==1.10.0
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] numpydoc==1.7.0
[conda] _anaconda_depends 2024.06 py312_mkl_2 https://repo.anaconda.com/pkgs/main
[conda] blas 1.0 mkl https://repo.anaconda.com/pkgs/main
[conda] mkl 2023.1.0 h213fc3f_46344 https://repo.anaconda.com/pkgs/main
[conda] mkl-service 2.4.0 py312h5eee18b_1 https://repo.anaconda.com/pkgs/main
[conda] mkl_fft 1.3.8 py312h5eee18b_0 https://repo.anaconda.com/pkgs/main
[conda] mkl_random 1.2.4 py312hdb19cb5_0 https://repo.anaconda.com/pkgs/main
[conda] numpy 1.26.4 py312hc5e2394_0 https://repo.anaconda.com/pkgs/main
[conda] numpy-base 1.26.4 py312h0da6c21_0 https://repo.anaconda.com/pkgs/main
[conda] numpydoc 1.7.0 py312h06a4308_0 https://repo.anaconda.com/pkgs/main

[larryliu0820]

@cccclai is anyone actively looking at this?