danielkrause/colibri-strix
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
95 Commits 1 Branch 0 Tags
97c756a06472b2f632453f35a541b2f0553bec00
Commit Graph

54 Commits

Author SHA1 Message Date
JustVugg b2855c0da1 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>
 2026-07-06 16:59:27 +02:00
JustVugg 3e88e37ba2 learning cache + true sampling + DSA indexer extraction mode 
- Learning cache: expert usage persists in <SNAP>/.coli_usage across sessions
  (atomic save every turn); at startup the hottest experts are auto-pinned in
  RAM with half the expert budget (AUTOPIN=0 disables). The engine gets faster
  the more you use it.
- Sampling: temperature + nucleus (official 1.0/0.95 defaults in chat; TEMP=0
  = greedy). MTP/n-gram speculation stays lossless via rejection sampling
  (accept draft w.p. p(draft); on reject resample with draft banned).
- coli: --temp flag.
- Converter: --indexer mode extracts DSA lightning-indexer weights
  (resumable; needed for future sparse attention beyond 2048 ctx).
- pin_load/stats include the MTP row; usage histogram covers layer 78.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-07-06 12:29:13 +02:00
JustVugg 257c4d0a8b serve: :piu resumes a truncated answer from live KV; ngen default 1024 (stops end turns now) 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-07-06 11:54:47 +02:00
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