feat(strata): build the MMQ prompt path
CI / check (push) Has been cancelled

Strata 0.2.14 leaves llama.cpp's MMQ prompt kernels out by default, so
STRATA_MMQ_KQ does nothing and UD-Q5_K_XL's Q6_K layer runs on Strata's
int8 kernel. On ms-s1-max, 0.2.15 with the gfx1151 prompt set and
STRATA_MMQ_KQ=1 gives first-token logits bit-identical to 0.2.13 over
15 cold prompts at the same speed (~1180 tok/s at 16K); without MMQ an
agent prompt reached KL 0.199 against 0.2.13. The engine grows from 39
to 54 MB.

Bead: nix-overlay-481
This commit is contained in:
2026-11-16 21:42:33 +03:00
parent b3287c926f
commit 7bb05ea685
2 changed files with 4 additions and 0 deletions
+3
View File
@@ -52,6 +52,9 @@ stdenv.mkDerivation (finalAttrs: {
"-DSTRATA_ENABLE_HIP=ON"
"-DSTRATA_ENABLE_CUDA=OFF"
"-DSTRATA_PREFILL_MMQ=ON"
# Off upstream since 0.2.14. With it, STRATA_MMQ_KQ=1 keeps UD-Q5_K_XL's
# Q6_K layer on MMQ: the same logits as 0.2.13, at the same prompt speed.
"-DSTRATA_MMQ=ON"
"-DSTRATA_BUILD_TESTS=OFF"
"-DSTRATA_PORTABLE=ON"
"-DCMAKE_HIP_ARCHITECTURES=gfx1151"