Files
colibri-strix/c/Makefile
T
JustVugg 1ae22a6135 colibrì: pure-C GLM-5.2 (744B MoE) engine with disk-streamed experts
Engine (c/glm.c): MLA attention with compressed KV, sigmoid noaux_tc router,
int8/int4/int2 quant kernels (AVX2), per-layer LRU expert cache + pinned
hot-store, batch-union MoE, native MTP speculative decoding (lossless),
multi-stop + official chat template, RAM auto-budget from MemAvailable.
Tokenizer: byte-level BPE in C. Tooling: coli CLI, disk-safe FP8→int4
converter, tiny-random oracle validation (TF 32/32, greedy 20/20).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-05 20:57:25 +02:00

23 lines
724 B
Makefile

CC = gcc
# ARCH=native -> ottimizzato per QUESTA macchina (default, piu' veloce).
# ARCH=x86-64-v3 -> binario PORTABILE su qualsiasi x86-64 moderno con AVX2 (per distribuire).
# ARCH=x86-64 -> massima compatibilita' (niente AVX2: usa il path scalare di fallback).
ARCH ?= native
CFLAGS = -O3 -march=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
LDFLAGS = -lm -fopenmp
all: glm
glm: glm.c st.h json.h tok.h tok_unicode.h
$(CC) $(CFLAGS) glm.c -o glm $(LDFLAGS)
olmoe: olmoe.c st.h json.h
$(CC) $(CFLAGS) olmoe.c -o olmoe $(LDFLAGS)
# binario portabile da distribuire su altre macchine x86-64
portable:
$(MAKE) glm ARCH=x86-64-v3
clean:
rm -f olmoe glm