From 10dddaab7aa2d61d6eb2a414b486b33352c29ac9 Mon Sep 17 00:00:00 2001 From: "K. Isom" Date: Fri, 18 Sep 2026 00:00:37 -0700 Subject: [PATCH] straylight: unwire Laguna DFlash until the GGUF matches llama.cpp Official laguna-s-2.1-DFlash-BF16.gguf is on disk but this llama.cpp rejects it (expected 76 tensors, got 69). Leave the draft unwired so Laguna loads; keep amdgpu DPM high. --- hw/straylight/default.nix | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/hw/straylight/default.nix b/hw/straylight/default.nix index 9db292d..731402f 100644 --- a/hw/straylight/default.nix +++ b/hw/straylight/default.nix @@ -39,16 +39,11 @@ let ; Poolside Laguna S 2.1 (118B total, 8B active): primary coding agent. ; ~69 GB of weights, so it only loads once the raised TTM/GTT limit is active (reboot). - ; DFlash draft (~2.2 GB BF16) from poolside/Laguna-S-2.1-GGUF. Keep draft KV in - ; f16; q8 draft KV collapses acceptance. spec-draft-n-max 4 is the gfx1151 - ; sweet spot (n=15 is the trained cap and is slower here). + ; DFlash GGUF is on disk (laguna-s-2.1-DFlash-BF16.gguf). nixpkgs llama.cpp 0.4.0 + ; rejects it at load ("expected 76, got 69" tensors); Poolside's file needs their + ; laguna-branch loader. Leave unwired so Laguna still starts. [laguna-s-2.1] model = ${llamaModelsDir}/laguna-s-2.1-UD-Q4_K_S/Laguna-S-2.1-UD-Q4_K_S-00001-of-00003.gguf - model-draft = ${llamaModelsDir}/laguna-s-2.1-UD-Q4_K_S/laguna-s-2.1-DFlash-BF16.gguf - spec-type = draft-dflash - spec-draft-n-max = 4 - cache-type-k-draft = f16 - cache-type-v-draft = f16 ; Two slots sharing one unified 131072-token KV pool: a second request (subagent, ; another client) runs alongside instead of queueing, and either one may still use ; the full 131072 as long as their combined context fits.