Run frontier MoE models on hardware you already own β pure C, zero deps, experts streamed from disk. Tiny engine, immense model. π¦
C
tools: deprecate convert_olmoe.py β its split gate/up/down layout no longer loads in olmoe.c
Zixin Zhoud616f39e6ce2
diff --git a/.gitignore b/.gitignoreindex f62b3792..08c4405d 100644--- a/.gitignore+++ b/.gitignore@@ -68,3 +68,4 @@ olmoe_merged/olmoe_i4/c/olmoe_merged/c/olmoe_i4/+.ideadiff --git a/c/tools/convert_olmoe.py b/c/tools/convert_olmoe.pyindex dc25f6a7..203ac868 100644--- a/c/tools/convert_olmoe.py+++ b/c/tools/convert_olmoe.py@@ -1,6 +1,10 @@#!/usr/bin/env python3"""Convert OLMoE HuggingFace checkpoint to colibri int4 format.+DEPRECATED: produces the split gate_proj/up_proj/down_proj tensor layout. The+current engine (olmoe.c) only loads the merged 'merged_weight' format β use+convert_olmoe_merged.py instead.+Downloads or converts a local OLMoE checkpoint (e.g., allenai/OLMoE-1B-7B-0125-Instruct).Dense weights stay as-is (engine reads BF16/F16 β F32 on load).Expert weights get row-wise symmetric quantization to --ebits bits (default 4)@@ -16,6 +20,12 @@ Usage:import argparse, json, math, os, struct, sysfrom pathlib import Path+sys.exit(+ "convert_olmoe.py is deprecated: it produces the split gate_proj/up_proj/down_proj\n"+ "tensor layout, but the current engine (olmoe.c) only loads the merged 'merged_weight'\n"+ "format. Use convert_olmoe_merged.py instead."+)+# Windows: force UTF-8 outputif sys.platform == "win32":for s in (sys.stdout, sys.stderr):