#2083 bench: community report, RTX 5060 Ti 16 GB + RTX 3060 12 GB unequal layer split (PCIe gen5 x8 + gen3 x4), IQ3_S, engine 0.1.43

说明

## What this is

A community benchmark report from an unequal two-card rig, answering `docs/TEST_REQUESTS.md` row 1 (two NVIDIA cards of different sizes, `--layer-split auto`) and A/B-ing the two live 0.1.43 default debates (#2010/#1975 overlap, route tail-skip) on a **split**. Note: the overlap turned out to be disabled on layer splits, so only the tail-skip A/B tests a live feature here; the overlap arm is a null control (see finding 4 in #2085). Those threads measured single-GPU only.

Results-only: one new folder, `bench/results/2026-10-11-community-rtx-5060ti-3060-split/`, no engine changes. The branch is from tag `v0.1.43` (`7695859a`), the exact commit the engine was built from (plus one local `setup.py`-only pip->uv commit; no engine code touched).

## Hardware

"bertha" - Ryzen 9 7900X, 64 GB DDR5-6400, Linux (CachyOS, engine in systemd-nspawn), driver 615.71.09, CUDA 13.4.

- **RTX 5060 Ti 16 GB** on PCIe **5.0 x8** - measured H2D 28.2-28.7 GB/s
- **RTX 3060 12 GB** on PCIe **3.0 x4** behind the chipset - measured H2D 3.15-3.2 GB/s

Links and H2D measured under load with `tools/h2d_bench`. The auto-generated `machine` block is unusable on this host (#2062) and was hand-corrected; the original values and every other edit are listed in `NOTES.md`.

## Model

Qwen3.8-Flash-Next **IQ3_S** (ISTA-DASLab GSQ-RCO pack, sha256 in `sha256sums.txt`), 512K context (yarn 2.0), pinned expert profile - no `--expert-profile-save` anywhere.

## Configurations tested

All `tools/strata_bench.py --long --runs 3`, one continuous evening session, 0 failures, `/metrics?requests=all` per-request histories included.

| run | config |
| --- | --- |
| A | baseline `--layer-split 40` |
| B1 | `--layer-split auto` (planner chose K=3) |
| B1c | explicit `--layer-split 6` (the engine's printed suggestion, followed literally) |
| B1d | explicit `--layer-split 42` (the as-given-frame equivalent) |
| C | baseline + `STRATA_ADAPT_OVERLAP=0` (null control: overlap is already off on a split) |
| D | baseline + `STRATA_ROUTE_TAIL_SKIP=0` |
| needles | `needle_bench.py` 32K/128K/256K x depths 10/50/90: **9/9 found** |

## Headline numbers

- Baseline: 32K prompt **1,721 tok/s**, short-chat decode **74.4 tok/s**.
- `auto` costs **-25.0%** of 32K prompt throughput (chunk clamp, #1616).
- The literal printed suggestion costs **-76%**: explicit splits do not inherit the #1352 card reorder - a question for maintainers is in the report.
- Tail-skip measures **+5.2%** here, not +10-20%, and decays with context; `ADAPT_OVERLAP` is **inert on layer splits** - the engine disables it before reading the flag (corrected after review in #2010; see commit 79cc236).
- Hit rate tracks **per-layer coverage**, not held-expert count (8,842 vs 5,935 held, statistically identical hit rate).

## Not tested

Long soak, batching/concurrency, vision latency, mmap file tier, Windows/HIP, single-card configs on this box. `hit_rate` is the decode-phase metric only.

## Discussion

The announcement issue with the full findings: #2085. The C and D rows were also posted as comments on #2010 and #2007; the #2010 comment's overlap conclusion was corrected afterwards (see the correction comment in #2010 and finding 4 in #2085).

*Drafted with AI assistance; I reviewed every line and ran the measurements myself.*