 Frank
|
b2a74004df
|
frank-large: swap to Kairic Edge 27B IU4 (W4A4) on Strix Halo
Replace the unsloth llama.cpp prebuilt (b11030, Qwen3.8-Flash-Next
UD-IQ4_XS, 125B MoE) with the Kairic Edge runtime (ciru-ai/ROCmFPX,
branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5) serving
jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (27B dense, IU4 W4A4).
- Runtime: built from source (scripts/build-kairic-edge-gfx1151.sh),
TheRock 7.15.0a20260718 toolchain, CK fdf4bb7f + gfx1151-iu4 patch.
- Shape: one stream, full 262144 context (the model's native window),
1 slot, 8 GiB prompt-cache budget.
- Spec method: native MTP depth 4 + n-gram drafting (24/64/64). DFlash
is NOT available for this model (no DRAFT_DFLASH spec type).
- Compatibility mode: the harness needs sampling, tools and a reasoning
budget, which fast-greedy rejects. COMPATIBILITY_MODE=1 enables them.
- Reasoning: enabled (auto + deepseek format, thoughts land in
reasoning_content).
- Payload: 4 files (15.5 GiB GGUF + 7.99 GiB FFN + 1.88 GiB GDN + 0.70
GiB GDN-Output), sha256-verified (scripts/download-frank-large-kairic.sh).
|
2026-09-21 18:56:35 -07:00 |
|