0xhis 7d8d5f3109 Reduce allocation overhead in quantized matmul and MoE routing (thread-local scratch, trimmed temporaries) (#43) ...

* Reuse quantization scratch buffers

* Trim MoE routing temporaries

---------

Co-authored-by: 0xhis <0xhis@users.noreply.github.com>

2026-07-11 12:59:01 +02:00

..

scripts

Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22)

2026-07-10 10:08:39 +02:00

tests

Isolated sequence KV contexts: KVState extraction, KV_SLOTS serve contexts with per-slot persistence, budget-aware pool accounting (#29)

2026-07-10 16:19:43 +02:00

tools

Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22)

2026-07-10 10:08:39 +02:00

backend_cuda.cu

Tiered CUDA acceleration for routed experts (opt-in, CPU default untouched) + REPLAY fixture harness (#16)

2026-07-10 07:41:09 +02:00

backend_cuda.h

Tiered CUDA acceleration for routed experts (opt-in, CPU default untouched) + REPLAY fixture harness (#16)

2026-07-10 07:41:09 +02:00

coli

Isolated sequence KV contexts: KVState extraction, KV_SLOTS serve contexts with per-slot persistence, budget-aware pool accounting (#29)

2026-07-10 16:19:43 +02:00

compat.h

macOS/Apple Silicon port: NEON kernels + platform shim (PR #1 by RDouglasSharp)

2026-07-06 22:01:12 +02:00

glm.c

Reduce allocation overhead in quantized matmul and MoE routing (thread-local scratch, trimmed temporaries) (#43)

2026-07-11 12:59:01 +02:00

iobench.c

macOS/Apple Silicon port: NEON kernels + platform shim (PR #1 by RDouglasSharp)

2026-07-06 22:01:12 +02:00

json.h

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

2026-07-05 20:57:25 +02:00

Makefile

REPIN follows live session heat (decaying heat map; .coli_usage stays the persistent signal) + disk→RAM→VRAM promotion (#26)

2026-07-10 12:48:53 +02:00

olmoe.c

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

2026-07-05 20:57:25 +02:00

openai_server.py

Isolated sequence KV contexts: KVState extraction, KV_SLOTS serve contexts with per-slot persistence, budget-aware pool accounting (#29)

2026-07-10 16:19:43 +02:00

ref_glm.json

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

2026-07-05 20:57:25 +02:00

resource_plan.py

coli plan: read-only Disk/RAM/VRAM placement planner (mirrors engine budget math, versioned --json, --auto-tier) (#27)

2026-07-10 12:51:23 +02:00

setup.sh

Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22)

2026-07-10 10:08:39 +02:00

st.h

macOS/Apple Silicon port: NEON kernels + platform shim (PR #1 by RDouglasSharp)

2026-07-06 22:01:12 +02:00

tier.h

REPIN follows live session heat (decaying heat map; .coli_usage stays the persistent signal) + disk→RAM→VRAM promotion (#26)

2026-07-10 12:48:53 +02:00

tok_unicode.h

Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22)

2026-07-10 10:08:39 +02:00

tok.h

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

2026-07-05 20:57:25 +02:00