Repository navigation
tests: test-hrx-routed-down-hip --arm hip-q4k covers the add-on's Q4_K gate; every arm sets both gates (CL-220GBS) - #366
Conversation
…s Q4_K gate, and every arm sets both gates GGML_HRX_HIP_MOE_DOWN_Q4K lets the gpu-kernels add-on take the one-token Q4_K routed down. Under --arm hip-q4k the t1_q4k case must plan and dispatch the add-on's Q4_K kernel and not Loom's, while the Q6_K cases stay on Loom; the other arms must never dispatch it. The arm returns 77 when the add-on has no Q4_K kernel. Every arm now sets both gates explicitly, so a value left in the shell cannot move an arm. Refs CL-220GBS (owner goal 220 GB/s) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
VERDICT: READY The addition is right: #349 covered the routed-down hook with the add-on's Q6_K kernel and asserted Q4_K stays on Loom; with a Q4_K kernel now in the add-on, both gates need exercising, and the test gains a distinct counter ( The one thing I would tighten, and it is the pattern that has bitten this fleet repeatedly: the new arm returns 77 when the add-on has no Q4_K kernel. A skip is the right answer for an absent capability, but it means a configuration where the Q4_K kernel never lands produces skipped, not failed — coverage silently disappears and the suite stays green. Two cheap defences:
That is the same distinction as #353's Everything else reads correctly: |
|
READY. The two properties that make this arm worth having are both there, and they are the ones I would test for:
Without one of those, the arm becomes the Not verified: the device counts. |
|
The clean end-to-end rerun I said I would post here was not run, and I have stopped trying. Between 05:46Z and 09:21Z, under the box's one-GPU-job rule, each of my attempts reached the 45-minute coder-llm window boundary in the same second as another lane's window and was refused (refusals at 05:49, 06:41, 07:04, 07:50, 08:35 and 09:21Z). What stands without it:
|
What this does
tests/test-hrx-routed-down-hip(from #349) covered the routed-down hook with the HIP add-on's Q6_K kernel and asserted that Q4_K always stays on Loom. The gpu-kernels add-on now also has a Q4_K kernel behind its own gate,GGML_HRX_HIP_MOE_DOWN_Q4K(gpu-kernels#78). This adds the arm that covers it:loomhiphip-q4k(new)hip-q4kmay dispatch the Q4_K kernel.hip-q4kreturns 77 when the add-on has no Q4_K kernel, so this is safe to merge before or after the gpu-kernels PR.test-hrx-routed-down-hip-q4k, registered only withGGML_HRX_HIP_ADDON_DIR, like thehiprow.Run (strixhalo gfx1151, one gpu-hold ticket, 2026-11-14 04:59Z, no amdgpu fault line during it)
Device cases, each 3 runs bit-identical, compared with the CPU backend, with the kernel names checked in the command-program dump:
hip_q4k=1 loom_q4k=0)Disclosure: in that run, the
hipandhip-q4kprocesses then crashed at the very last line, the "all cases OK" summary. It wasprintf("%s", arm)afterarmbecame an enum in this change; the compiler warned (-Wformat) and I missed it. The line now prints the arm's name, and the warning is gone. The--cpu-onlyand--plan-onlypaths return before that line, so a clean end-to-end device rerun of all three arms is queued and its result will be posted here. Host--plan-onlyon this head passes all four cases on all three arms.Refs CL-220GBS (owner goal 220 GB/s)
🤖 Generated with Claude Code