rocky-vulkan-llama

2 Commits 1 Branch 0 Tags

Author	SHA1	Message	Date
Claude (noether)	e74bae69fe	panvk WLS fix v1 + confirmed mechanism (partial: reuse halves but doesn't eliminate) Instrument-first panthor boot confirms Fable's diagnosis: ~326 per-dispatch WLS allocs exhaust the sub-4GB priv VA heap at ub>=128. Grow-only single-max reuse (fix v1) halves the pressure (326->715 dispatches) but WLS sizes vary 128x (155KB-19MB) so a single buffer is insufficient. Refined fix pending 2nd review. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-07-11 14:06:47 +02:00
Claude (noether)	16b96537fd	rocky-vulkan-llama: skeleton — deps, root-cause diagnosis, llama.cpp submit patch Documents the RK3588 Mali-G610 GPU-prefill stack (panthor + panvk + llama.cpp Vulkan), the panvk ub64 OOM blocker, and collects the ggml-vulkan tunable-submit patch. Mesa panvk fix pending root-cause confirmation (see docs/root-cause.md). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-07-11 13:33:00 +02:00

Author

SHA1

Message

Date

Claude (noether)

e74bae69fe

panvk WLS fix v1 + confirmed mechanism (partial: reuse halves but doesn't eliminate)

Instrument-first panthor boot confirms Fable's diagnosis: ~326 per-dispatch WLS allocs
exhaust the sub-4GB priv VA heap at ub>=128. Grow-only single-max reuse (fix v1) halves the
pressure (326->715 dispatches) but WLS sizes vary 128x (155KB-19MB) so a single buffer is
insufficient. Refined fix pending 2nd review.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-11 14:06:47 +02:00

Claude (noether)

16b96537fd

rocky-vulkan-llama: skeleton — deps, root-cause diagnosis, llama.cpp submit patch

Documents the RK3588 Mali-G610 GPU-prefill stack (panthor + panvk + llama.cpp Vulkan),
the panvk ub64 OOM blocker, and collects the ggml-vulkan tunable-submit patch. Mesa panvk
fix pending root-cause confirmation (see docs/root-cause.md).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-11 13:33:00 +02:00