multi-repo-dsv4flash-setup SKILL.md skillA
multi-repo-dsv4flash-setup from hw-native-sys/simpler is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hw-native-sys/simpler/multi-repo-dsv4flash-setup@git:20260721.f5e17fbPins git:20260721.f5e17fb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hw-native-sys/simpler
- Path
.claude/skills/multi-repo-dsv4flash-setup/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260721.f5e17fb, committed Jul 21, 2026
- Size
- 9,308 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
Concrete guide to benchmark DeepSeek-V4 (dsv4) FLASH on NPU against the current worktree's simpler — the three decode attentions (swa/csa/hca) and the distributed MoE, all in pypto-lib's models/deepseek/v4/. Defers cross-repo clone/install to multi-repo-setup, then gives the exact PYPTO_BENCH run commands and the hard-won config that makes the numbers reproducible: pin ptoas 0.48 (0.50/ptoas-bin cannot compile csa), pin --start-pos 8192, edit moe.py for 16 experts/card, read fast_effective_us…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# DeepSeek-V4 FLASH on NPU: attention + MoE effective-time benchmark This skill is the **dsv4-flash-specific concrete guide**. It benchmarks the four kernels that live in **pypto-lib** at `models/deepseek/v4/` against the current worktree's simpler: | kernel | file | measures | dies | | ------ | ---- | -------- | ---- | | SWA attention | `decode_attention_swa.py` | decode attn effective_us | 1 | | CSA attention | `decode_attention_csa.py` | decode attn effective_us | 1 | | HCA attention | `decode_attention_hca.py` | decode attn effective_us | 1 | | MoE (distributed) | `moe.py` | decode MoE fast_effective_us | ≥2 (EP) | It sits on top of [`multi-repo-setup`](../multi-repo-setup/SKILL.md), which owns the generic repo-graph + clone + install steps this skill does not repeat. Everything below is the dsv4-specific run recipe and the five configuration facts that make the effective-time numbers **reproducible to ~1%** instead of wandering ±18% run-to-run. ## 1. Setup — defer to multi-repo-setup Run [`multi-repo-setup`](../multi-repo-setup/SKILL.md) first — it clones pto-isa / pypto / pypto-lib under `build/`, exports the toolchain env, and …
Read the whole file at its exact version.
How to install
mdr add hw-native-sys/simpler/multi-repo-dsv4flash-setup@sha256:b584dbff9c6fed77The line at the top of this page pins the label git:20260721.f5e17fb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4wdjw34efxpiatf6)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 21, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9308 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hw-native-sys/simpler · 46 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4wdjw34efxpiatf6 GET https://markdownregistry.com/api/v1/resolve?ref=hw-native-sys/simpler/multi-repo-dsv4flash-setup GET https://markdownregistry.com/api/v1/blob/b584dbff9c6fed772661ca0f7909460df5398a17632fb83304716ae59e8b58f3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.