Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| ca39e5333f | |||
| 741d46ba25 | |||
| 3cd2674f68 | |||
| e25aeecc4c | |||
| 2f8fefd701 | |||
| c90e2cc438 | |||
| d86a6b93ad |
@@ -0,0 +1,10 @@
|
||||
BasedOnStyle: LLVM
|
||||
IndentWidth: 4
|
||||
ColumnLimit: 120
|
||||
AllowShortFunctionsOnASingleLine: All
|
||||
AllowShortIfStatementsOnASingleLine: AllIfsAndElse
|
||||
AllowShortLoopsOnASingleLine: true
|
||||
BreakBeforeBraces: Attach
|
||||
PointerAlignment: Right
|
||||
SpaceAfterCStyleCast: false
|
||||
SortIncludes: false
|
||||
@@ -0,0 +1,24 @@
|
||||
root = true
|
||||
|
||||
[*]
|
||||
charset = utf-8
|
||||
end_of_line = lf
|
||||
insert_final_newline = true
|
||||
trim_trailing_whitespace = true
|
||||
indent_style = space
|
||||
indent_size = 4
|
||||
|
||||
[*.{c,h,cu}]
|
||||
indent_size = 4
|
||||
|
||||
[*.{ts,tsx,js,json,css}]
|
||||
indent_size = 2
|
||||
|
||||
[Makefile]
|
||||
indent_style = tab
|
||||
|
||||
[*.yml]
|
||||
indent_size = 2
|
||||
|
||||
[*.md]
|
||||
trim_trailing_whitespace = false
|
||||
@@ -24,7 +24,9 @@ jobs:
|
||||
name: windows-x86_64
|
||||
ext: ".exe"
|
||||
make_args: ""
|
||||
shell: msys2
|
||||
# GitHub shells are format strings: 'msys2 {0}', never bare 'msys2'
|
||||
# (the v1.0.0 tag build failed on exactly this). Same as ci.yml.
|
||||
shell: "msys2 {0}"
|
||||
runs-on: ${{ matrix.os }}
|
||||
defaults:
|
||||
run:
|
||||
@@ -32,11 +34,14 @@ jobs:
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- if: matrix.shell == 'msys2'
|
||||
- if: matrix.os == 'windows-latest'
|
||||
uses: msys2/setup-msys2@v2
|
||||
with:
|
||||
msystem: UCRT64
|
||||
update: false
|
||||
# inherit: the Package step calls the runner's 7z.exe, which lives on
|
||||
# the Windows PATH; the default minimal path would not see it.
|
||||
path-type: inherit
|
||||
install: >-
|
||||
make
|
||||
mingw-w64-ucrt-x86_64-gcc
|
||||
|
||||
@@ -183,6 +183,10 @@ COLI_MODEL=/nvme/glm52_i4 ./coli doctor # read-only readiness check
|
||||
The engine at runtime is pure C — python is only used by the one-time converter
|
||||
and the optional API gateway.
|
||||
|
||||
Prefer a `coli` command on your PATH? From a checkout, `pip install -e .`
|
||||
registers it (the engine itself still lives in `c/` — this is an editable
|
||||
install from the clone, not a standalone wheel).
|
||||
|
||||
### 3. Go deeper
|
||||
|
||||
| topic | doc |
|
||||
|
||||
@@ -4924,7 +4924,68 @@ static int repin_pick(Model *m, RepinCand *out, int maxc){
|
||||
}
|
||||
return nb;
|
||||
}
|
||||
/* ---- RSS GUARD (#403) -----------------------------------------------------
|
||||
* La proiezione di cap_for_ram e' una STIMA: sul GB10 (#403) le generazioni
|
||||
* lunghe l'hanno sforata di ~40 GB (proiettato 74.4, reale 115.6 -> 3 kill del
|
||||
* kernel). La run D dell'issue prova che un cap piu' basso CONTIENE la crescita:
|
||||
* questa guardia lo fa da sola, sull'RSS MISURATO invece che sul proiettato.
|
||||
* Al safe point (stessa sede di repin: nessun moe in volo), ogni ~16 token
|
||||
* emessi: se l'RSS supera il budget, svuota gli slot LRU meno usati e abbassa
|
||||
* ecap perche' non ricrescano. Gli slab sono >128KB (mmap'd da glibc): la free
|
||||
* restituisce le pagine al kernel subito, quindi l'RSS scende davvero.
|
||||
* Lo slot NON viene compattato via: resta al suo posto con eid=-1/used=0 (primo
|
||||
* candidato al riuso), perche' con PILOT_REAL il worker tiene puntatori dentro
|
||||
* ecache[] durante i suoi pread e uno spostamento li invaliderebbe; per lo
|
||||
* stesso motivo gli slot eid<0 (riservati/in caricamento) non si toccano e la
|
||||
* selezione avviene sotto g_pilot_mx. resident_bytes resta invariato: gli slot
|
||||
* LRU non sono mai contati li' (solo pin e densa).
|
||||
* EN: evict = free the slab in place (eid=-1, used=0, never compact: PILOT_REAL
|
||||
* EN: holds pointers into ecache[] across its preads), skip eid<0 reservations,
|
||||
* EN: select under g_pilot_mx. RSS_GUARD_GB=<gb> forces an explicit ceiling. */
|
||||
static double g_ram_budget_gb=0; /* budget risolto, scritto da cap_for_ram */
|
||||
static uint64_t g_rssg_last=0;
|
||||
static void rss_guard(Model *m){
|
||||
double lim = getenv("RSS_GUARD_GB") ? atof(getenv("RSS_GUARD_GB")) : g_ram_budget_gb;
|
||||
if(lim<=0) return;
|
||||
if(m->n_emit - g_rssg_last < 16) return;
|
||||
g_rssg_last = m->n_emit;
|
||||
double rss=rss_gb();
|
||||
if(rss <= lim*1.02+0.3) return; /* tolleranza: 2% + 300MB */
|
||||
Cfg *c=&m->c;
|
||||
int64_t need=(int64_t)((rss-lim)*1e9), freed=0; int dropped=0;
|
||||
for(int pass=0; pass<8 && freed<need; pass++){
|
||||
for(int l=0; l<=c->n_layers && freed<need; l++){
|
||||
if(!m->ecache || !m->ecache[l]) continue;
|
||||
pthread_mutex_lock(&g_pilot_mx);
|
||||
int nn=m->ecn[l], lru=-1;
|
||||
for(int z=0;z<nn;z++){ /* solo slot pubblicati e con slab */
|
||||
ESlot *cand=&m->ecache[l][z];
|
||||
if(cand->eid<0 || !cand->slab) continue;
|
||||
if(lru<0 || cand->used<m->ecache[l][lru].used) lru=z;
|
||||
}
|
||||
if(lru<0){ pthread_mutex_unlock(&g_pilot_mx); continue; }
|
||||
ESlot *s=&m->ecache[l][lru];
|
||||
s->eid=-1; /* nascosto: nessun hit/evict altrui */
|
||||
pthread_mutex_unlock(&g_pilot_mx);
|
||||
int64_t sb=s->slab_cap + s->fslab_cap*4;
|
||||
#ifdef COLI_METAL
|
||||
if(s->slab && g_metal_enabled) coli_metal_unregister(s->slab);
|
||||
#endif
|
||||
compat_aligned_free(s->slab); free(s->fslab);
|
||||
s->slab=NULL; s->fslab=NULL; s->slab_cap=s->fslab_cap=0;
|
||||
QT *q[3]={&s->g,&s->u,&s->d};
|
||||
for(int k=0;k<3;k++){ q[k]->qf=NULL; q[k]->q8=NULL; q[k]->q4=NULL; q[k]->s=NULL; }
|
||||
s->used=0; /* primo candidato al riuso */
|
||||
freed += sb; dropped++;
|
||||
}
|
||||
if(m->ecap>2) m->ecap--; /* il tetto scende: niente ricrescita */
|
||||
}
|
||||
if(dropped)
|
||||
fprintf(stderr,"[RAM-GUARD] RSS %.1f GB over the %.1f GB budget (#403): "
|
||||
"dropped %d cached experts, cap -> %d\n", rss, lim, dropped, m->ecap);
|
||||
}
|
||||
static void repin_pass_limit(Model *m,int limit){
|
||||
rss_guard(m); /* #403: il budget si fa rispettare sull'RSS MISURATO */
|
||||
if(g_repin<=0) return;
|
||||
if(m->n_emit - g_last_repin < (uint64_t)g_repin) return;
|
||||
g_last_repin = m->n_emit;
|
||||
@@ -6024,6 +6085,7 @@ static void cap_for_ram(Model *m, double ram_gb, int ebits, int max_ctx){
|
||||
if(auto_b){ ram_gb = g_mem_avail_boot*0.88; /* misurata PRIMA del load: il residente gia'
|
||||
* allocato viene sottratto sotto, non due volte */
|
||||
if(ram_gb<4){ fprintf(stderr,"[RAM] MemAvailable is unreadable or too low; assuming 8 GB\n"); ram_gb=8; } }
|
||||
g_ram_budget_gb = ram_gb; /* #403: la RSS-guard usa il budget RISOLTO */
|
||||
/* slack ONESTO, non forfettario (l'OOM del 2026-07-04 veniva da qui):
|
||||
* ws[64] slab del working-set (si materializzano TUTTI nel prefill batch-union),
|
||||
* KV cache a max_ctx, kvb_all della ricostruzione k/v in attention,
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""colibrì — tiny engine, immense model."""
|
||||
|
||||
from colibri._version import __version__
|
||||
|
||||
__all__ = ["__version__"]
|
||||
@@ -0,0 +1,23 @@
|
||||
"""Version accessor for the pip package.
|
||||
|
||||
The single source of truth is c/version.py (#394): coli --version and the
|
||||
GitHub Release workflow read it, so the pip metadata must read the SAME file
|
||||
instead of carrying a second literal that would drift on the first bump.
|
||||
|
||||
From a checkout (the supported install: `pip install -e .`) the file is read
|
||||
directly. From an installed wheel c/ is not on disk, so fall back to the
|
||||
package metadata that setuptools baked at build time from that same file.
|
||||
"""
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
_ns = {}
|
||||
exec((Path(__file__).resolve().parent.parent / "c" / "version.py").read_text(), _ns)
|
||||
__version__ = _ns["__version__"]
|
||||
except OSError:
|
||||
from importlib.metadata import PackageNotFoundError, version
|
||||
|
||||
try:
|
||||
__version__ = version("colibri-engine")
|
||||
except PackageNotFoundError:
|
||||
__version__ = "0.0.0+unknown"
|
||||
@@ -0,0 +1,30 @@
|
||||
"""Entry point for `coli` when installed via pip.
|
||||
|
||||
Delegates to the original c/coli script which handles all subcommands.
|
||||
This wrapper exists so `pip install colibri-engine` creates a `coli` console
|
||||
script that works without the user having to add c/ to PATH manually.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import runpy
|
||||
|
||||
|
||||
def main():
|
||||
here = os.path.dirname(os.path.abspath(__file__))
|
||||
engine_dir = os.path.join(os.path.dirname(here), "c")
|
||||
coli_script = os.path.join(engine_dir, "coli")
|
||||
|
||||
if not os.path.exists(coli_script):
|
||||
sys.exit(
|
||||
"colibri engine directory not found.\n"
|
||||
"Install from source: git clone + pip install -e ."
|
||||
)
|
||||
|
||||
sys.path.insert(0, engine_dir)
|
||||
sys.argv[0] = coli_script
|
||||
runpy.run_path(coli_script, run_name="__main__")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,53 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=68.0"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "colibri-engine"
|
||||
dynamic = ["version"]
|
||||
description = "Tiny engine, immense model — run GLM-5.2 (744B MoE) locally"
|
||||
readme = "README.md"
|
||||
license = "Apache-2.0"
|
||||
requires-python = ">=3.10"
|
||||
authors = [
|
||||
{name = "JustVugg"},
|
||||
]
|
||||
classifiers = [
|
||||
"Development Status :: 4 - Beta",
|
||||
"Environment :: Console",
|
||||
"Intended Audience :: Science/Research",
|
||||
"Operating System :: POSIX :: Linux",
|
||||
"Operating System :: MacOS",
|
||||
"Operating System :: Microsoft :: Windows",
|
||||
"Programming Language :: Python :: 3",
|
||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
convert = [
|
||||
"numpy",
|
||||
"huggingface_hub",
|
||||
]
|
||||
oracle = [
|
||||
"torch>=2.0",
|
||||
"transformers>=4.40",
|
||||
"safetensors",
|
||||
]
|
||||
bench = [
|
||||
"tokenizers",
|
||||
"datasets",
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
coli = "colibri.cli:main"
|
||||
|
||||
[project.urls]
|
||||
Homepage = "https://github.com/JustVugg/colibri"
|
||||
Issues = "https://github.com/JustVugg/colibri/issues"
|
||||
|
||||
[tool.setuptools.dynamic]
|
||||
version = {attr = "colibri._version.__version__"}
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
where = ["."]
|
||||
include = ["colibri*"]
|
||||
Reference in New Issue
Block a user