colibrì: pure-C GLM-5.2 (744B MoE) engine with disk-streamed experts

Browse Source

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>

...

This commit is contained in:

JustVugg

2026-07-05 20:52:05 +02:00

parent a6deef8e44

commit 1ae22a6135

32 changed files with 4440 additions and 1 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

c/glm.c

+1282

File diff suppressed because it is too large Load Diff