| |
| """Upload the project code, docs and measurement results to the HF repo.""" |
|
|
| from __future__ import annotations |
|
|
| import argparse |
| import os |
| import sys |
| from pathlib import Path |
|
|
| from huggingface_hub import HfApi |
|
|
| |
| REPO = Path(__file__).resolve().parent.parent |
|
|
| MSG = """EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M |
| |
| Port the 8 GiB expert pager to openbmb/MiniCPM-V-4.7-35B-A3B-Q4_K_M.gguf |
| (19.71 GiB, qwen35moe, 40 layers, 256 experts, top-8). |
| |
| Measured under an 8 GiB / no-swap ceiling enforced by tools/strict8g.py: |
| 5.83 tok/s median (N=9), peak anon RSS 7799 MiB, VmSwap 0, 9/9 strict_ok. |
| Unmodified llama.cpp cannot load the model at that ceiling. |
| |
| Correctness: 3-layer verification passes; 5 runs x 48 tokens x 248144 vocab |
| logits bit-identical. |
| |
| Port-specific changes: GGUF BOOL-array header fix, calibrated SDQ_RESERVE_MB, |
| two expert size classes, hybrid SSM/attention thread behaviour. |
| """ |
|
|
|
|
| def main() -> int: |
| ap = argparse.ArgumentParser() |
| ap.add_argument("--repo", default=os.environ.get("EPM_HF_REPO", "HelloSun/minicpm47woek")) |
| ap.add_argument("--folder", default=str(REPO)) |
| ap.add_argument("--message", default=MSG) |
| ap.add_argument("--dry-run", action="store_true") |
| a = ap.parse_args() |
|
|
| api = HfApi() |
| print("whoami:", api.whoami()["name"]) |
| if a.dry_run: |
| print("dry run, not uploading") |
| return 0 |
| api.upload_folder( |
| folder_path=a.folder, |
| repo_id=a.repo, |
| repo_type="model", |
| ignore_patterns=[".git/*", "__pycache__/*", "*.pyc", "*.so", |
| "bench/results/.*", "*.gguf", "*.bin"], |
| commit_message=a.message, |
| ) |
| print(f"uploaded -> https://huggingface.co/{a.repo}") |
| return 0 |
|
|
|
|
| if __name__ == "__main__": |
| sys.exit(main()) |
