url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: split glm.c into colibri.c + 4 header modules

Browse Source 
Rename glm.c → colibri.c and extract four self-contained modules
into header-only files (same pattern as st.h/tier.h/grammar.h):

  quant.h      (672 lines) — SIMD matmul kernels, quantization
  sample.h     (143 lines) — RNG, top-p sampling, stop-set
  kv_persist.h (121 lines) — .coli_kv disk persistence
  telemetry.h  (189 lines) — dashboard protocol, stats, usage

Main engine file shrinks from 6588 to 5396 lines (−18%).

Build system: primary target is now colibri$(EXE); `make glm`
remains as a phony alias for backward compat. CI, setup.sh,
coli CLI, and all 10 test files that include the engine are
updated. make check passes (C + Python, 73 tests, zero warnings).
This commit is contained in:
ZacharyZcR
2026-07-19 03:56:56 +08:00
parent 8f33bd153b
commit f853ea8a0b
21 changed files with 1206 additions and 1265 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/coli
+10 -6
View File
@@ -54,16 +54,20 @@ from version import __version__ as _version
# guess is right (e.g. a custom packaging layout).
_EXE = ".exe" if sys.platform == "win32" else ""
_LIBEXEC = os.path.join(os.path.dirname(HERE), "libexec", "colibri")
_here_colibri = os.path.join(HERE, "colibri" + _EXE)
_here_glm = os.path.join(HERE, "glm" + _EXE)
if os.environ.get("COLI_ENGINE"):
GLM = os.environ["COLI_ENGINE"]
TOOLS = os.path.join(os.path.dirname(GLM), "tools")
elif os.path.exists(_here_colibri):
GLM = _here_colibri
TOOLS = os.path.join(HERE, "tools")
elif os.path.exists(_here_glm):
GLM = _here_glm
TOOLS = os.path.join(HERE, "tools")
else:
GLM = os.path.join(_LIBEXEC, "glm" + _EXE)
GLM = os.path.join(_LIBEXEC, "colibri" + _EXE)
TOOLS = os.path.join(_LIBEXEC, "tools")
sys.path.insert(0, _LIBEXEC) # so `import resource_plan`, `doctor`, `openai_server` still resolve
@@ -241,13 +245,13 @@ def env_for(a):
e["COLI_CUDA"]="0"; e.pop("CUDA_EXPERT_GB",None); e.pop("CUDA_DENSE",None)
else:
if not cuda_binary():
sys.exit(f"{C.yel}--gpu needs the CUDA build:{C.r} make glm CUDA=1 (this binary is CPU-only)")
sys.exit(f"{C.yel}--gpu needs the CUDA build:{C.r} make colibri CUDA=1 (this binary is CPU-only)")
e["COLI_CUDA"]="1"
if a.gpu!="auto": e["COLI_GPUS"]=a.gpu
e.setdefault("CUDA_DENSE","1")
if a.vram and a.gpu!="none":
if not cuda_binary():
sys.exit(f"{C.yel}--vram needs the CUDA build:{C.r} make glm CUDA=1 (this binary is CPU-only)")
sys.exit(f"{C.yel}--vram needs the CUDA build:{C.r} make colibri CUDA=1 (this binary is CPU-only)")
e["COLI_CUDA"]="1"; e["CUDA_EXPERT_GB"]=str(a.vram)
return e
@@ -421,8 +425,8 @@ def cmd_build(a):
banner("build")
if not os.path.exists(os.path.join(HERE, "Makefile")):
sys.exit(f"{C.yel}coli build{C.r} only works from a source checkout (this is an installed copy).\n"
f" Clone https://github.com/JustVugg/colibri and run ./setup.sh, or make -C c glm.")
sys.exit(subprocess.call(["make","-C",HERE,"glm"]))
f" Clone https://github.com/JustVugg/colibri and run ./setup.sh, or make -C c colibri.")
sys.exit(subprocess.call(["make","-C",HERE,"colibri"]))
def cmd_info(a):
banner("info")
@@ -802,7 +806,7 @@ def cmd_stop(a):
if "coli" in cmd and " serve" in cmd and pid!=os.getpid():
if not any(p==pid for p,_ in targets): targets.append((pid,"coli serve (cmdline)"))
comm=open(f"/proc/{pd}/comm").read().strip()
if comm in ("glm","exe","olmoe"):
if comm in ("colibri","glm","exe","olmoe"):
env=open(f"/proc/{pd}/environ","rb").read().replace(b"\0",b"\n").decode("utf-8","replace")
if "SERVE=1" in env: targets.append((pid,f"engine `{comm}` (SERVE=1)"))
except (OSError,PermissionError): continue