From fc7d8e32be862e1ddb39aac407968244138f4eb0 Mon Sep 17 00:00:00 2001 From: bong-water-water-bong Date: Sat, 14 Nov 2026 15:41:45 -0400 Subject: [PATCH 1/2] config: gpu-kernels pin 965936607 -> 260115d6d (27B Q4_K prefill on the HIP dense-prefill kernels, +26 %; the m64 swiglu tile registered) gpu-kernels 96593660..260115d6d is four PRs: - #79 / #80: the plain m64 swiglu tile is built and swiglu_tile() asks for it below 256 tokens; - #81, reverted by #83: no net change (the HIP MoE down kernels stay opt-in); - #84: 256-aligned Q4_K prefill on a weight decode reads stored goes to the HIP dense-prefill kernels instead of Loom's q8_1_x4 kernel (69 % of a 27B Q4_K_M ubatch), and the plain m64 swiglu tile #79 built is registered. Without that registration, every HIP swiglu batch under 256 tokens fails on gpu-kernels main ("cataloged kernel ... is not available in the active corpus", 1bit serve's warm-up returns 500), so #79 must not be pinned without #84. Measured on Qwen3.8-27B Q4_K_M, gfx1151 (gpu-kernels#84, issuecomment-6882820957): paired interleaved A/B x3, 2,200-token prefill +25.6 % warm / +26.0 % cold (medians.py: disjoint); KLD 32 x 512 vs the old routing 0.000277, same top p 99.29 %. Co-Authored-By: Claude Opus 5.5 --- config/gpu-kernels.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/config/gpu-kernels.config b/config/gpu-kernels.config index 1dc9a9907..e475efefc 100644 --- a/config/gpu-kernels.config +++ b/config/gpu-kernels.config @@ -22,6 +22,6 @@ # # Move the pin by hand, after the HRX checks on Strix Halo (docs/hrx.md). repo=1bit-MONSTER/gpu-kernels -sha=96593660718d5babe52703f7a93e3bcc9d3f4608 +sha=260115d6d5d19ed12cc98b4304dffa786e8059db path=addons/hip-hrx require=addon.cmake kernels From 71204977973864653082d52a0ac0ed4902231c20 Mon Sep 17 00:00:00 2001 From: bong-water-water-bong Date: Sat, 14 Nov 2026 16:01:07 -0400 Subject: [PATCH 2/2] config: gpu-kernels pin -> 6105368c5 (adds #85: probe fix, tile-completeness check, GGML_HRX_HIP_DENSE_PREFILL_Q4K_STORED=0 opt-out) Co-Authored-By: Claude Opus 5.5 --- config/gpu-kernels.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/config/gpu-kernels.config b/config/gpu-kernels.config index e475efefc..87d0692cf 100644 --- a/config/gpu-kernels.config +++ b/config/gpu-kernels.config @@ -22,6 +22,6 @@ # # Move the pin by hand, after the HRX checks on Strix Halo (docs/hrx.md). repo=1bit-MONSTER/gpu-kernels -sha=260115d6d5d19ed12cc98b4304dffa786e8059db +sha=6105368c58d387666a56d554be2b5a2fc2ca2a5f path=addons/hip-hrx require=addon.cmake kernels