Nanogpt loading in llm_manual section is failed

[yv0vaa]

🐛 Describe the bug

I completely followed this guide (I ran strictly the same commands in the same sequence) and noticed that adding the following assert into the main.cpp function kills the program

...
int main() {
    ...
    Module model("nanogpt.pte", Module::LoadMode::MmapUseMlockIgnoreErrors);
    assert(model.is_loaded());
    ...
}

However without this assert generate function (somehow) works, but output is strange:

(executorch) vl.zakharov@nn-ai-int-36:~/nanogpt_example$ ./nanogpt_runner 
Enter model prompt: Hi, how are you?
Hi, how are you doing?

I'm doing fine. I'm doing fine. I'm doing fine. I'm doing fine. I'm doing fine. I

Versions

PyTorch version: 2.5.0+cpu
Is debug build: False
CUDA used to build PyTorch: Could not collect
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04 LTS (x86_64)
GCC version: (Ubuntu 13.2.0-23ubuntu4) 13.2.0
Clang version: Could not collect
CMake version: version 3.31.4
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-6.8.0-38-generic-x86_64-with-glibc2.39
Is CUDA available: False
CUDA runtime version: 12.0.140
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 4090
Nvidia driver version: 550.90.07
cuDNN version: Could not collect
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): 24
On-line CPU(s) list: 0-23
Vendor ID: GenuineIntel
Model name: 12th Gen Intel(R) Core(TM) i9-12900
CPU family: 6
Model: 151
Thread(s) per core: 2
Core(s) per socket: 16
Socket(s): 1
Stepping: 2
CPU(s) scaling MHz: 32%
CPU max MHz: 5100,0000
CPU min MHz: 800,0000
BogoMIPS: 4838,40
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq tme rdpid movdiri movdir64b fsrm md_clear serialize pconfig arch_lbr ibt flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 640 KiB (16 instances)
L1i cache: 768 KiB (16 instances)
L2 cache: 14 MiB (10 instances)
L3 cache: 30 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-23
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: Mitigation; Clear Register File
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
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==0.4.0a0+6a085ff
[pip3] numpy==1.21.3
[pip3] torch==2.5.0+cpu
[pip3] torchaudio==2.5.0+cpu
[pip3] torchsr==1.0.4
[pip3] torchvision==0.20.0+cpu
[conda] executorch 0.4.0a0+6a085ff pypi_0 pypi
[conda] numpy 1.21.3 pypi_0 pypi
[conda] torch 2.5.0+cpu pypi_0 pypi
[conda] torchaudio 2.5.0+cpu pypi_0 pypi
[conda] torchsr 1.0.4 pypi_0 pypi
[conda] torchvision 0.20.0+cpu pypi_0 pypi

cc @mergennachin @cccclai @helunwencser @dvorjackz

[yv0vaa]

I have just observed that prompting with the same phrase as in the example gives the same output:

(base) vl.zakharov@nn-server-dev-58:~/nanogpt_example$ ./cmake-out/nanogpt_runner 
Enter model prompt: Hello world!
Hello world!

I'm not sure if you've heard of the "Curse of the Dragon" or not, but it's a very popular game in

I hope it can help

[tarun292]

@yv0vaa looks like you were asserting before calling load() on the Module so that would be expected. As far as the output of the model is concerned, can you try some of the other models such as Llama 1B or 3B and see what sorts of outputs you are getting?

[yv0vaa]

I added the following

...
int main() {
  ...
  Module model("nanogpt.pte", Module::LoadMode::MmapUseMlockIgnoreErrors);
  auto error = model.load();
  assert(error == Error::Ok);
  assert(model.is_loaded());
  ...
}

and now this asserts are passed, however model output with Hello world! prompt hadn't changed. With prompt Hi, how are you things are getting stranger:

(executorch) vl.zakharov@nn-ai-int-36:~/nanogpt_example$ ./nanogpt_runner 
Enter model prompt: Hi, how are you?
Hi, how are you?

I'm a little bit of a nerd. I'm a big nerd. I'm a big nerd. I'm a big nerd. I

To my opinion even if this behavior is correct, it worth adding model.load() to the guide. Now I'm going to try load Llama as you mentioned