Run frontier MoE models on hardware you already own β pure C, zero deps, experts streamed from disk. Tiny engine, immense model. π¦
C
Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22)
ZacharyZcR13e8f09ffc09
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex e215c76d..a85b8602 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -7,9 +7,12 @@ Keep changes focused and preserve Colibri's dependency-free default CPU path.Run the lightweight checks locally:```sh-make -C c check+make check```+`make -C c check` remains available for scripts that already run from the+engine directory.+This performs one portable CPU build, C unit tests, and Python standard-librarytests. It does not download a model or require CUDA.diff --git a/Makefile b/Makefilenew file mode 100644index 00000000..4da2ce13--- /dev/null+++ b/Makefile@@ -0,0 +1,4 @@+.PHONY: all glm portable test check cuda-test clean++all glm portable test check cuda-test clean:+ $(MAKE) -C c $@diff --git a/README.md b/README.mdindex 5114ce90..c0e1b75c 100644--- a/README.md+++ b/README.md@@ -36,7 +36,7 @@ The engine is a single C file (`c/glm.c`, ~1,300 lines) plus small headers. No B- **Batch-union MoE**: in prefill (and MTP verification), each unique expert of the batch is read once and applied to every position that routes to it.- **Byte-level BPE tokenizer in C** (GPT-2-style with Unicode-property regex, 320k merges).- **RAM safety**: the expert cache is auto-sized from `MemAvailable` at startup β an honest peak projection (working set, KV, MTP row, reconstruction buffers) so the kernel OOM-killer never fires.-- **Offline FP8βint4 converter** (`c/convert_fp8_to_int4.py`): downloads one shard at a time (~5 GB), dequants (128Γ128 block scales), requantizes to the engine's container, deletes the shard β the 756 GB FP8 checkpoint never needs to exist on disk at once. Resumable.+- **Offline FP8βint4 converter** (`c/tools/convert_fp8_to_int4.py`): downloads one shard at a time (~5 GB), dequants (128Γ128 block scales), requantizes to the engine's container, deletes the shard β the 756 GB FP8 checkpoint never needs to exist on disk at once. Resumable.## Honest numbers (WSL2, 12 cores, 25 GB RAM, NVMe via VHDX)@@ -147,8 +147,8 @@ deterministic 313M-parameter `glm_moe_dsa` fixture and run fixed-token replay:```bashcd c-python make_glm_bench_model.py --output /nvme/colibri-bench-medium --device cuda-python benchmark_cuda_fixture.py --model /nvme/colibri-bench-medium --gpu 0+python tools/make_glm_bench_model.py --output /nvme/colibri-bench-medium --device cuda+python tools/benchmark_cuda_fixture.py --model /nvme/colibri-bench-medium --gpu 0```The fixture has random weights and is not a language model. It exists only to@@ -242,16 +242,26 @@ Every contribution, from a datapoint to a disk, moves the ceiling.## Repo layout```-c/glm.c the engine (GLM-5.2 forward, streaming MoE, MTP, serve mode)-c/st.h safetensors reader: pread + fadvise, no mmap (RSS stays flat)-c/tok.h byte-level BPE tokenizer in C-c/coli CLI: chat / run / bench / convert / info-c/iobench.c parallel disk microbenchmark (measures what the engine feels)-c/convert_fp8_to_int4.py disk-safe FP8 β int4 converter-c/make_glm_oracle.py tiny-random oracle generator for validation-c/olmoe.c stage-A engine (OLMoE), first validation target+Makefile root build/check entry point+c/+βββ glm.c single-file GLM engine+βββ st.h, tok.h, json.h runtime headers+βββ backend_cuda.* optional CUDA tier+βββ Makefile build and local checks+βββ coli user-facing CLI+βββ setup.sh one-command local setup+βββ tools/ offline conversion, fixtures and benchmarks+βββ scripts/ long-running conversion helpers+βββ tests/ dependency-free C and Python tests```+The runtime path intentionally stays flat and readable: `glm.c` plus its small+headers. Auxiliary Python and shell tooling is grouped separately and is never a+runtime dependency of the engine.++From the repository root, `make`, `make check`, and `make clean` delegate to the+engine Makefile. Existing commands run from `c/` continue to work unchanged.+## Why "colibrΓ¬"The hummingbird weighs a few grams, hovers in place, and visits a thousand flowers a day. This engine keeps a 744-billion-parameter giant alive on hummingbird rations: 25 GB of RAM, twelve CPU cores, and a lot of disk patience.diff --git a/c/Makefile b/c/Makefileindex 04101df2..5921c5cf 100644--- a/c/Makefile+++ b/c/Makefile@@ -56,9 +56,9 @@ backend_cuda.o: backend_cuda.cu backend_cuda.h@command -v $(NVCC) >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }$(NVCC) $(NVCCFLAGS) -c backend_cuda.cu -o $@-cuda-test: backend_cuda.cu backend_cuda.h backend_cuda_test.cu+cuda-test: backend_cuda.cu backend_cuda.h tests/test_backend_cuda.cu@command -v $(NVCC) >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }- $(NVCC) $(NVCCFLAGS) backend_cuda.cu backend_cuda_test.cu -o backend_cuda_test+ $(NVCC) $(NVCCFLAGS) backend_cuda.cu tests/test_backend_cuda.cu -o backend_cuda_test./backend_cuda_testolmoe: olmoe.c st.h json.h@@ -82,7 +82,7 @@ test-python:test: test-c test-python-# CI-friendly validation: one portable CPU build and dependency-free tests.+# Local validation: one portable CPU build and dependency-free tests.check:$(MAKE) clean$(MAKE) portablediff --git a/c/coli b/c/coliold mode 100644new mode 100755index f1022ecf..5e304b7c--- a/c/coli+++ b/c/coli@@ -19,6 +19,7 @@ Config via env o flag (validi anche dopo il sottocomando):import os, sys, subprocess, argparse, json, time, signal, shutil, threading, re, codecs, tempfile, textwrapHERE = os.path.dirname(os.path.abspath(__file__))+TOOLS = os.path.join(HERE, "tools")GLM = os.path.join(HERE, "glm")DEF_MODEL = os.environ.get("COLI_MODEL", "/home/vincenzo/glm52_i4")END = b"\x01\x01END\x01\x01\n"@@ -385,9 +386,9 @@ def cmd_bench(a):missing=[t for t in tasks.split(",") if not os.path.exists(os.path.join(a.data,f"{t}.jsonl"))]if missing:print(f" {C.dim}scarico i dataset mancanti: {', '.join(missing)}{C.r}")- subprocess.call([py, os.path.join(HERE,"fetch_benchmarks.py"),+ subprocess.call([py, os.path.join(TOOLS,"fetch_benchmarks.py"),"--out", a.data, "--tasks", ",".join(missing), "--limit", str(max(a.limit,200))])- cmd=[py, os.path.join(HERE,"eval_glm.py"), "--snap",a.model,+ cmd=[py, os.path.join(TOOLS,"eval_glm.py"), "--snap",a.model,"--tasks", tasks, "--limit", str(a.limit), "--data", a.data]if a.ram: cmd+=["--ram",str(a.ram)]e=dict(os.environ)@@ -401,7 +402,7 @@ def cmd_convert(a):# python con torch/safetensors: l'ambiente del progetto se c'e', altrimenti quello correntevenv_py=os.path.join(HERE,"mio_env","bin","python3")py = venv_py if os.path.exists(venv_py) else sys.executable- base=[py, os.path.join(HERE,"convert_fp8_to_int4.py"),+ base=[py, os.path.join(TOOLS,"convert_fp8_to_int4.py"),"--repo", a.repo, "--outdir", a.model, "--ebits", str(a.ebits), "--io-bits", str(a.io_bits)]if a.xbits: base+=["--xbits",str(a.xbits)]# passo 1: modello principale (78 layer). Resumabile: riparte dagli shard mancanti.diff --git a/c/glm.c b/c/glm.cindex 6d0604ba..292ae238 100644--- a/c/glm.c+++ b/c/glm.c@@ -12,7 +12,7 @@* E' cio' che fa entrare GLM-5.2 nei 15 GB: ~17B param residenti a int4 ~= 8.7 GB.* Norme/router/bias restano f32 (piccoli e sensibili).*- * Validazione: stessi token id di ref_glm.json (oracolo transformers, c/make_glm_oracle.py).+ * Validazione: stessi token id di ref_glm.json (oracolo transformers, c/tools/make_glm_oracle.py).* build: make glm run: SNAP=./glm_tiny ./glm <cap> <expert_bits> <dense_bits>* TF=1 -> teacher-forcing (valida il prefill su tutta la sequenza)*/diff --git a/c/run.sh b/c/scripts/run.shold mode 100644new mode 100755similarity index 80%rename from c/run.shrename to c/scripts/run.shindex 1cbcd35b..6c797ca8--- a/c/run.sh+++ b/c/scripts/run.sh@@ -1,14 +1,14 @@#!/usr/bin/env bash# Pipeline GLM-5.2 (int4, streaming, 15 GB RAM) β tutto in WSL, modello su ext4.-# uso: ./run.sh ["prompt"] [n_token]+# uso da c/: scripts/run.sh ["prompt"] [n_token]# Fa: (1) attende lo spostamento su ext4, (2) riprende la conversione fino a completarla,# (3) compila il motore, (4) genera testo restando nel budget RAM.set -euo pipefail-DIR=/home/vincenzo/glm52_i4 # modello int4 su ext4 (NON /mnt/c!)-REPO=zai-org/GLM-5.2-FP8-CODE=/mnt/c/Users/User/Desktop/moe-stream/c-RAM_GB=15+DIR="${COLI_MODEL:-/home/vincenzo/glm52_i4}" # modello int4 su ext4 (NON /mnt/c!)+REPO="${COLI_REPO:-zai-org/GLM-5.2-FP8}"+CODE="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"+RAM_GB="${RAM_GB:-15}"PROMPT="${1:-Ciao, chi sei?}"NGEN="${2:-64}"@@ -25,7 +25,7 @@ echo "[1/4] spostamento completato: $(du -sh "$DIR" | cut -f1), shard $(ls "$DIR# 2) riprende+completa la conversione (ripartibile: salta gli shard gia' fatti)echo "[2/4] conversione (riprende da dove era): output -> $DIR"-python3 convert_fp8_to_int4.py --repo "$REPO" --outdir "$DIR" --ebits 4 --io-bits 8+python3 tools/convert_fp8_to_int4.py --repo "$REPO" --outdir "$DIR" --ebits 4 --io-bits 8# 3) il motore richiede tokenizer.json + config.json nella dir del modellofor f in config.json tokenizer.json; dodiff --git a/c/supervisor.sh b/c/scripts/supervisor.shold mode 100644new mode 100755similarity index 87%rename from c/supervisor.shrename to c/scripts/supervisor.shindex 144aa32c..bba41846--- a/c/supervisor.sh+++ b/c/scripts/supervisor.sh@@ -4,11 +4,11 @@# - se un download resta FERMO >180s (connessione zombie), lo ammazza e lo rilancia:# hf_hub riprende il .incomplete dal punto esatto, non si perde nulla# - esce da solo quando tutti i 141 shard sono fatti-# uso: nohup ./supervisor.sh > supervisor.log 2>&1 &+# uso da c/: nohup scripts/supervisor.sh > supervisor.log 2>&1 &set -u-DIR=/home/vincenzo/glm52_i4-CODE=/mnt/c/Users/User/Desktop/moe-stream/c-TOTAL=141+DIR="${COLI_MODEL:-/home/vincenzo/glm52_i4}"+CODE="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"+TOTAL="${TOTAL_SHARDS:-141}"STALL_S=180 # secondi senza crescita del download -> riavvioCONVLOG=/tmp/convert_supervised.log@@ -19,7 +19,7 @@ log(){ echo "[$(date +%H:%M:%S)] $*"; }start_conv(){cd "$CODE"- nohup python3 convert_fp8_to_int4.py --repo zai-org/GLM-5.2-FP8 \+ nohup python3 tools/convert_fp8_to_int4.py --repo zai-org/GLM-5.2-FP8 \--outdir "$DIR" --ebits 4 --io-bits 8 >> "$CONVLOG" 2>&1 &log "convertitore avviato (PID $!)"}diff --git a/c/setup.sh b/c/setup.shold mode 100644new mode 100755diff --git a/c/backend_cuda_test.cu b/c/tests/test_backend_cuda.cusimilarity index 99%rename from c/backend_cuda_test.curename to c/tests/test_backend_cuda.cuindex cc28ef6e..f72b4fd2 100644--- a/c/backend_cuda_test.cu+++ b/c/tests/test_backend_cuda.cu@@ -1,4 +1,4 @@-#include "backend_cuda.h"+#include "../backend_cuda.h"#include <cmath>#include <cstdio>diff --git a/c/tests/test_benchmark_cuda_fixture.py b/c/tests/test_benchmark_cuda_fixture.pyindex 4ff34dd6..542a7da1 100644--- a/c/tests/test_benchmark_cuda_fixture.py+++ b/c/tests/test_benchmark_cuda_fixture.py@@ -1,6 +1,6 @@import unittest-from benchmark_cuda_fixture import parse_output+from tools.benchmark_cuda_fixture import parse_outputSAMPLE = """diff --git a/c/tok_test.c b/c/tests/test_tok.csimilarity index 96%rename from c/tok_test.crename to c/tests/test_tok.cindex 986e50f8..10562f8e 100644--- a/c/tok_test.c+++ b/c/tests/test_tok.c@@ -1,8 +1,8 @@/* Validazione del tokenizer C contro l'oracolo HF.- * build: gcc -O2 tok_test.c -o tok_test+ * build da c/: gcc -O2 tests/test_tok.c -o tok_test* uso: ./tok_test <tokenizer.json> (legge righe "TEXT\tID,ID,.." da stdin) */#define _GNU_SOURCE-#include "tok.h"+#include "../tok.h"int main(int argc, char **argv){if(argc<2){ fprintf(stderr,"uso: %s tokenizer.json < casi\n",argv[0]); return 1; }diff --git a/c/tok_unicode.h b/c/tok_unicode.hindex c0839c27..62959de8 100644--- a/c/tok_unicode.h+++ b/c/tok_unicode.h@@ -1,4 +1,4 @@-/* GENERATO da gen_unicode.py β non modificare a mano. */+/* GENERATO da tools/gen_unicode.py β non modificare a mano. */#ifndef TOK_UNICODE_H#define TOK_UNICODE_H#include <stdint.h>diff --git a/c/tools/README.md b/c/tools/README.mdnew file mode 100644index 00000000..20937885--- /dev/null+++ b/c/tools/README.md@@ -0,0 +1,16 @@+# Tools++These scripts support model preparation and offline engineering work. They are+not runtime dependencies of the C engine.++- `convert_fp8_to_int4.py`, `download_glm52.py`: model preparation+- `make_glm_oracle.py`, `make_glm_bench_model.py`: deterministic fixtures+- `benchmark_cuda_fixture.py`, `eval_glm.py`, `fetch_benchmarks.py`: benchmarks+- `gen_unicode.py`: tokenizer table generation++Run them from `c/`, for example:++```sh+python3 tools/convert_fp8_to_int4.py --selftest+python3 tools/make_glm_bench_model.py --output /tmp/colibri-bench+```diff --git a/c/tools/__init__.py b/c/tools/__init__.pynew file mode 100644index 00000000..aaa0579b--- /dev/null+++ b/c/tools/__init__.py@@ -0,0 +1 @@+"""Offline conversion, fixture, benchmark, and evaluation utilities."""diff --git a/c/benchmark_cuda_fixture.py b/c/tools/benchmark_cuda_fixture.pysimilarity index 97%rename from c/benchmark_cuda_fixture.pyrename to c/tools/benchmark_cuda_fixture.pyindex 73a30db6..7352ed47 100644--- a/c/benchmark_cuda_fixture.py+++ b/c/tools/benchmark_cuda_fixture.py@@ -1,4 +1,4 @@-"""Reproducible CPU/CUDA A/B benchmark for make_glm_bench_model.py output."""+"""Reproducible CPU/CUDA A/B benchmark for tools/make_glm_bench_model.py output."""import argparseimport jsondiff --git a/c/convert_fp8_to_int4.py b/c/tools/convert_fp8_to_int4.pysimilarity index 99%rename from c/convert_fp8_to_int4.pyrename to c/tools/convert_fp8_to_int4.pyindex 5785ee94..4ba18124 100644--- a/c/convert_fp8_to_int4.py+++ b/c/tools/convert_fp8_to_int4.py@@ -19,11 +19,11 @@ dati impacchettati, `nome.qs` F32 = scale per riga).USO:# test locale (oracolo tiny, niente download): converte una dir gia' presente- python3 convert_fp8_to_int4.py --indir glm_tiny --outdir glm_tiny_i4 --ebits 4 --io-bits 4+ python3 tools/convert_fp8_to_int4.py --indir glm_tiny --outdir glm_tiny_i4 --ebits 4 --io-bits 4# selftest del dequant fp8 (richiede torch)- python3 convert_fp8_to_int4.py --selftest+ python3 tools/convert_fp8_to_int4.py --selftest# reale: scarica+converte+cancella shard per shard- python3 convert_fp8_to_int4.py --repo zai-org/GLM-5.2-FP8 --outdir /home/vincenzo/glm52_i4+ python3 tools/convert_fp8_to_int4.py --repo zai-org/GLM-5.2-FP8 --outdir /home/vincenzo/glm52_i4"""import os, sys, glob, json, shutil, argparseimport numpy as npdiff --git a/c/download_glm52.py b/c/tools/download_glm52.pysimilarity index 90%rename from c/download_glm52.pyrename to c/tools/download_glm52.pyindex 56889673..544a3f62 100644--- a/c/download_glm52.py+++ b/c/tools/download_glm52.py@@ -9,8 +9,8 @@ NB: i pesi sono F8_E4M3 + tensori `*.weight_scale_inv` (blocchi 128x128). Il loadeve supportare fp8+block-scale prima di poterli usare (vedi memoria glm52-specs).USO:- python3 download_glm52.py # scarica tutto in /home/vincenzo/glm52 (ripartibile)- python3 download_glm52.py --check # solo stima spazio e conteggio file, niente download+ python3 tools/download_glm52.py # scarica tutto in /home/vincenzo/glm52 (ripartibile)+ python3 tools/download_glm52.py --check # solo stima spazio e conteggio file, niente downloadLo scaricamento e' di centinaia di GB e ore: lancialo tu quando il resto e' pronto."""diff --git a/c/eval_glm.py b/c/tools/eval_glm.pysimilarity index 91%rename from c/eval_glm.pyrename to c/tools/eval_glm.pyindex 7de1c00f..83778b1c 100644--- a/c/eval_glm.py+++ b/c/tools/eval_glm.py@@ -7,20 +7,20 @@ Serve a capire se la quantizzazione int4 ha lasciato il modello "tale" rispettopunteggi PUBBLICATI di GLM-5.2 (e, per contesto, Claude/GPT).Dipendenze: solo `tokenizers` + il binario ./glm. I dataset si leggono da JSONL locali-(uno per task) prodotti da `fetch_benchmarks.py`. Formato di ogni riga JSONL:+(uno per task) prodotti da `tools/fetch_benchmarks.py`. Formato di ogni riga JSONL:{"ctx": "...", "choices": ["...","..."], "gold": 0}Cosi' la harness e' offline e deterministica.USO:# 1) (una volta, quando hai rete) scarica i benchmark in ./bench/*.jsonl- python3 fetch_benchmarks.py --out ./bench --tasks hellaswag,arc_challenge,mmlu --limit 200+ python3 tools/fetch_benchmarks.py --out ./bench --tasks hellaswag,arc_challenge,mmlu --limit 200# 2) plumbing test della meccanica (senza motore):- python3 eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench --tasks smoke --dry+ python3 tools/eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench --tasks smoke --dry# 3) validazione vera quando il modello e' pronto:- python3 eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench \+ python3 tools/eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench \--tasks hellaswag,arc_challenge,mmlu --limit 40 --ram 15# leve di ricerca: passate al motore via env- TOPP=0.9 python3 eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench --tasks mmlu --ram 15+ TOPP=0.9 python3 tools/eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench --tasks mmlu --ram 15"""import os, sys, subprocess, argparse, random, json, tempfile, time@@ -43,7 +43,7 @@ def load_docs(task, data_dir, limit, seed):return SMOKE[:limit] if limit else SMOKEpath = os.path.join(data_dir, task + ".jsonl")if not os.path.exists(path):- sys.exit(f"manca {path} β generalo con: python3 fetch_benchmarks.py --out {data_dir} --tasks {task}")+ sys.exit(f"manca {path} β generalo con: python3 tools/fetch_benchmarks.py --out {data_dir} --tasks {task}")docs = [json.loads(l) for l in open(path) if l.strip()]random.Random(seed).shuffle(docs)return docs[:limit] if limit else docs@@ -138,7 +138,7 @@ def main():print(f"(motore: {time.time()-t0:.0f}s){proc.stderr.strip().splitlines()[-1] if proc.stderr.strip() else ''}", file=sys.stderr)score_accuracy(tasks, meta, perq, lp)print("\nNB: confronta acc_norm col punteggio PUBBLICATO di GLM-5.2 (model card). Se vicino,"- "\n la quantizzazione int4 ha preservato il modello. (riempi REFERENCE in eval_glm.py)")+ "\n la quantizzazione int4 ha preservato il modello. (riempi REFERENCE in tools/eval_glm.py)")os.remove(req_path)if __name__ == "__main__":diff --git a/c/fetch_benchmarks.py b/c/tools/fetch_benchmarks.pysimilarity index 92%rename from c/fetch_benchmarks.pyrename to c/tools/fetch_benchmarks.pyindex b0200c99..d0069dce 100644--- a/c/fetch_benchmarks.py+++ b/c/tools/fetch_benchmarks.py@@ -4,9 +4,9 @@ Scarica i benchmark LLM standard e li converte nel formato JSONL della harnessRichiede `datasets`: pip install --break-system-packages datasets (o in una venv)USO:- python3 fetch_benchmarks.py --out ./bench --tasks hellaswag,arc_challenge,arc_easy,mmlu,winogrande,piqa,openbookqa --limit 300+ python3 tools/fetch_benchmarks.py --out ./bench --tasks hellaswag,arc_challenge,arc_easy,mmlu,winogrande,piqa,openbookqa --limit 300Poi:- python3 eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench --tasks mmlu --limit 40 --ram 15+ python3 tools/eval_glm.py --snap /home/vincenzo/glm52_i4 --data ./bench --tasks mmlu --limit 40 --ram 15"""import os, json, argparse, randomdiff --git a/c/gen_unicode.py b/c/tools/gen_unicode.pysimilarity index 93%rename from c/gen_unicode.pyrename to c/tools/gen_unicode.pyindex 14144884..780baa2c 100644--- a/c/gen_unicode.py+++ b/c/tools/gen_unicode.py@@ -4,7 +4,7 @@ pre-tokenizer cl100k (regex del tokenizer GLM-5.2):- \\p{N} numeri (categoria che inizia per 'N')- \\s whitespace (proprieta' Unicode White_Space)Ogni classe diventa un array ordinato di range [lo,hi] inclusivi; il C fa ricerca-binaria. Eseguire una volta: python3 gen_unicode.py > tok_unicode.h+binaria. Eseguire una volta: python3 tools/gen_unicode.py > tok_unicode.h"""import sys, unicodedata@@ -41,7 +41,7 @@ def emit(name, rs):print("};")print(f"static const int {name}_n = {len(rs)};\n")-print("/* GENERATO da gen_unicode.py β non modificare a mano. */")+print("/* GENERATO da tools/gen_unicode.py β non modificare a mano. */")print("#ifndef TOK_UNICODE_H\n#define TOK_UNICODE_H\n#include <stdint.h>\n")emit("uni_L", L); emit("uni_N", N); emit("uni_S", S)print("""static int uni_in(const uint32_t t[][2], int n, uint32_t cp){diff --git a/c/make_glm_bench_model.py b/c/tools/make_glm_bench_model.pysimilarity index 100%rename from c/make_glm_bench_model.pyrename to c/tools/make_glm_bench_model.pydiff --git a/c/make_glm_oracle.py b/c/tools/make_glm_oracle.pysimilarity index 100%rename from c/make_glm_oracle.pyrename to c/tools/make_glm_oracle.py