QNN Export Llama Model Error "failed to load context binary"

🐛 Describe the bug

Model: Samsung Galaxy S24 U
Chipset: Qualcomm SM8650-AC Snapdragon 8 Gen 3
NDK: r27c
QNN SDK:2.31

this is the command i am trying to run
python -m examples.models.llama.export_llama -t "/home/qaaiml-shreshth/exe_qualcomm/tokenizer.model" -p "/home/qaaiml-shreshth/exe_qualcomm/params.json" -c "/home/qaaiml-shreshth/exe_qualcomm/consolidated.00.pth" --use_kv_cache --qnn --pt2e_quantize qnn_16a4w -d fp32 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name="llama3.2new.pte" --disable_dynamic_shape --num_sharding 8 --calibration_tasks wikitext --calibration_limit 1 --calibration_seq_length 128 --calibration_data "<|start_header_id|>system<|end_header_id|>\n\nYou are a funny chatbot.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nCould you tell me about Facebook?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"

Versions

Collecting environment information...
PyTorch version: 2.7.0.dev20250131+cpu
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04.1 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version: Could not collect
CMake version: version 3.31.6
Libc version: glibc-2.39

Python version: 3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0] (64-bit runtime)
Python platform: Linux-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.39
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 22
On-line CPU(s) list: 0-21
Vendor ID: GenuineIntel
Model name: Intel(R) Core(TM) Ultra 7 155H
CPU family: 6
Model: 170
Thread(s) per core: 2
Core(s) per socket: 11
Socket(s): 1
Stepping: 4
BogoMIPS: 5990.39
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 tsc_reliable nonstop_tsc cpuid pni pclmulqdq vmx 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 tpr_shadow vnmi ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves avx_vnni umip waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize flush_l1d arch_capabilities
Virtualization: VT-x
Hypervisor vendor: Microsoft
Virtualization type: full
L1d cache: 528 KiB (11 instances)
L1i cache: 704 KiB (11 instances)
L2 cache: 22 MiB (11 instances)
L3 cache: 24 MiB (1 instance)
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; Enhanced IBRS
Vulnerability Spec rstack overflow: 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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected

Versions of relevant libraries:
[pip3] executorch==0.6.0a0+262f0f1
[pip3] numpy==2.2.3
[pip3] torch==2.7.0.dev20250131+cpu
[pip3] torchao==0.10.0+git7d879462
[pip3] torchaudio==2.6.0.dev20250131+cpu
[pip3] torchsr==1.0.4
[pip3] torchvision==0.22.0.dev20250131+cpu
[conda] executorch 0.6.0a0+262f0f1 pypi_0 pypi
[conda] numpy 2.2.3 pypi_0 pypi
[conda] torch 2.7.0.dev20250131+cpu pypi_0 pypi
[conda] torchao 0.10.0+git7d879462 pypi_0 pypi
[conda] torchaudio 2.6.0.dev20250131+cpu pypi_0 pypi
[conda] torchsr 1.0.4 pypi_0 pypi
[conda] torchvision 0.22.0.dev20250131+cpu pypi_0 pypi
(et_qnn) qaaiml-shreshth@DESKTOP-TLFOCL9:~$

cc @cccclai @winskuo-quic @shewu-quic @cbilgin

Start with the examples.models.llama.export_llama entry point and reproduce the command using the reported PyTorch, ExecuTorch, QNN SDK, and Android-device versions. Inspect the QNN export and context-binary steps referenced by the failure, then verify the generated Llama export on the Samsung Galaxy S24 Ultra. Done means the export completes without the “failed to load context binary” error, or the issue documents a reproducible root cause.