From e01484f6d02d8750b390d7cec91e57e27482530c Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Fri, 11 Sep 2026 19:18:53 -0700 Subject: [PATCH] memory: consolidate backref lines to true archival counts (was triple-counted) --- persistent-memory.md | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/persistent-memory.md b/persistent-memory.md index 31e55b7..8f69be3 100644 --- a/persistent-memory.md +++ b/persistent-memory.md @@ -362,17 +362,13 @@ _As of 2026-09-11 ~17:45 PT._ - `[2026-08-15]` **RP-seat direction: KEEP MeroMero on `char-rp`; Artemis-31B rejected; next move is Dark-Scarlett on a Qwen3.8 base when it lands (operator).** Evaluated `TheDrummer/Artemis-31B-v1.1` — mechanically a drop-in (same `google/gemma-4-31B-it` base, identical 1188-tensor/356-vision census, same missing-`preprocessor_config.json` trick), so it's purely a quality call, and our own survey already ranked MeroMero **#1** vs Artemis **#6**; Artemis is also unlicensed and its author deprioritizes correctness + warns of token-banning-for-stability, which fights char-rp's tool-calling requirement. **MTP verified impossible on both** (Gemma-4 has no MTP head at all — base/MeroMero/Artemis are all MTP=0; no finetune can add one). **But speculative decoding IS reachable on a Gemma-4 seat via a DETACHED drafter** — vLLM 0.24 supports `eagle3` + `gemma4_mtp`, and real drafters exist: `google/gemma-4-31B-it-assistant` (0.94 GB, 4-layer, 761K dl), `RedHatAI/gemma-4-31B-it-speculator.eagle3` (4.47 GB), `AEON-7/…eagle3-NVFP4` (3.53 GB). ⚠ all list their verifier as **stock** gemma-4-31B-it, not an RP finetune, so acceptance against MeroMero is unmeasured and likely well below the gen seat's ~48%. UNTESTED — parked, ~45 min to measure, needs GPU0 headroom (card is at 94.4/97.9 GB). **Why the Dark-Scarlett 3.8 plan is the strong one:** DS is Qwen3.6-based today, so a 3.8 respin lands on the *gen seat's* architecture → native MTP returns and the whole mixed NVFP4+FP8 recipe + graft ports directly. Watch two things on arrival: `from_pretrained` **silently drops MTP heads during finetuning** (verify 15 `mtp.*` tensors in the index; graft from stock if absent), and DS v1.0 required the `Qwen3_5ForConditionalGeneration` **wrapper class** to save a config vLLM/SGLang accept. Both in `docs/pfi/model-quantization-playbook.md`. -_285 older entries archived to archival-memory.md._ -_159 older entries archived to archival-memory.md._ -_4 older entries archived to archival-memory.md._ + +_20 older entries archived to archival-memory.md._ ## Tried and abandoned - `[2026-09-04]` **Forcing 10G on the ESH-Media DAC — it linked, then degraded over hours, and I reported a plateau at two minutes.** ⚠ A clean zero-error link at 1G does NOT rule out a marginal cable; autoneg's fallback was protecting something real. → `persistent-memory.d/2026-09-04-dac-forced-10g-failed.md` - -_152 older entries archived to archival-memory.md._ - -_1 older entries archived to archival-memory.md._ +_110 older entries archived to archival-memory.md._