coli convert: one command does model + MTP head; README documents the full zero-to-chat path

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

README.md

@@ -56,14 +56,21 @@ Cold starts are heavy on random reads (~11 GB/token). Reads themselves are safe,
 cd c
 ./setup.sh                      # checks gcc/OpenMP, builds, self-tests
 
-# convert the model (resumable, needs ~400 GB free on a real ext4/NVMe path):
+# ONE command does everything model-side: downloads GLM-5.2-FP8 shard by shard
-./coli convert                  # from zai-org/GLM-5.2-FP8
+# (never needs the full 756 GB at once), converts to the int4 container, then
+# converts the MTP head for speculative decoding. Resumable at any point.
+# Conversion (only) needs python with: pip install torch safetensors huggingface_hub numpy
+./coli convert --model /nvme/glm52_i4     # ~400 GB free on a real ext4/NVMe path
 
-# chat (RAM budget and expert cache size itself automatically):
+# chat — RAM budget, expert cache and MTP are all detected automatically:
-COLI_MODEL=/path/to/glm52_i4 ./coli chat
+COLI_MODEL=/nvme/glm52_i4 ./coli chat
 ```
 
-Useful knobs (env or flags): `--topp 0.7` adaptive expert top-p (30–40% less disk), `--ngen N` max tokens, `STATS=f`/`PIN=f PIN_GB=g` record expert usage then pin the hottest in RAM, `THINK=1` enable GLM-5.2's reasoning block, `DRAFT=n` MTP draft depth, `TF=1` teacher-forcing validation.
+The engine at runtime is pure C — python is only used by the one-time converter.
+
+Useful knobs (env or flags): `--temp 0.7` token sampling temperature (0 = greedy, default 1.0 + nucleus 0.95), `--topp 0.7` adaptive expert top-p (30–40% less disk), `--ngen N` max tokens per answer (`:piu` in chat continues a truncated one), `AUTOPIN=0` disable the learning cache's auto-pin, `THINK=1` enable GLM-5.2's reasoning block, `DRAFT=n` MTP draft depth, `TF=1` teacher-forcing validation.
+
+**The learning cache**: the engine records which experts your usage actually routes to (`.coli_usage` next to the model, updated every turn) and at startup automatically pins the hottest ones in spare RAM. colibrì literally gets faster the more you use it.
 
 ## Got a better machine? Try it — here's what to expect
 

c/coli

@@ -269,11 +269,20 @@ def cmd_bench(a):
 
 def cmd_convert(a):
     banner("convert")
-    cmd=[sys.executable, os.path.join(HERE,"convert_fp8_to_int4.py"),
+    # python con torch/safetensors: l'ambiente del progetto se c'e', altrimenti quello corrente
+    venv_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"),
           "--repo", a.repo, "--outdir", a.model, "--ebits", str(a.ebits), "--io-bits", str(a.io_bits)]
-    if a.xbits: cmd+=["--xbits",str(a.xbits)]
+    if a.xbits: base+=["--xbits",str(a.xbits)]
-    print(f"  {C.dim}{' '.join(cmd)}{C.r}")
+    # passo 1: modello principale (78 layer). Resumabile: riparte dagli shard mancanti.
-    sys.exit(subprocess.call(cmd))
+    print(f"  {C.dim}[1/2] modello: {' '.join(base)}{C.r}")
+    rc=subprocess.call(base)
+    if rc!=0: sys.exit(rc)
+    if a.no_mtp: sys.exit(0)
+    # passo 2: testa MTP (layer 78) -> abilita la decodifica speculativa nativa (piu' veloce)
+    print(f"  {C.dim}[2/2] testa MTP (draft speculativi){C.r}")
+    sys.exit(subprocess.call(base+["--mtp"]))
 
 def main():
     common=argparse.ArgumentParser(add_help=False)
@@ -290,6 +299,7 @@ def main():
     pb.add_argument("--limit",type=int,default=40); pb.add_argument("--data",default=os.path.join(HERE,"bench"))
     pc=sub.add_parser("convert", parents=[common]); pc.add_argument("--repo",default="zai-org/GLM-5.2-FP8")
     pc.add_argument("--ebits",type=int,default=4); pc.add_argument("--io-bits",type=int,default=8); pc.add_argument("--xbits",type=int,default=0)
+    pc.add_argument("--no-mtp",action="store_true",help="salta la testa MTP (niente draft speculativi)")
     a=ap.parse_args()
     {"build":cmd_build,"info":cmd_info,"run":cmd_run,"chat":cmd_chat,"bench":cmd_bench,
      "convert":cmd_convert}.get(a.cmd, lambda _:(banner(),print(__doc__)))(a)