dsv4-c64-1280tps-ascend-a3

dsv4-c64-1280tps-ascend-a3 is a skill for Claude Code from binrogithub/1-3-Cloud-Adoption-Skills. It costs 93 tokens per session (3,145 once invoked), scanned A, original, no licence file.

A deployment and benchmarking guide for running DeepSeek-V4-Flash-0731 in W8A8 format on an Ascend A3 AI accelerator at high concurrent throughput.

In plain words
What is it for?
It helps optimise DSV4 with Fused MC2 and DSpark, tune high-concurrency serving, and reproduce the stated throughput result.
Why use it?
It focuses on tuning the system for many simultaneous requests and a target aggregate output rate, rather than only validating that the model runs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps optimise DSV4 with Fused MC2 and DSpark, tune high-concurrency serving, and reproduce the stated throughput result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add binrogithub/1-3-Cloud-Adoption-Skills --skill dsv4-c64-1280tps-skill
Clone the repo
git clone --depth 1 https://github.com/binrogithub/1-3-Cloud-Adoption-Skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dsv4-c64-1280tps-ascend-a3

README.md
[![agentmods](https://agentmods.dev/badge/skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill/github.svg)](https://agentmods.dev/skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill)
Your own site
<a href="https://agentmods.dev/skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill"><img src="https://agentmods.dev/badge/skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dsv4-c64-1280tps-ascend-a3

Your own site · 80×15
<a href="https://agentmods.dev/skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill"><img src="https://agentmods.dev/badge/skills/binrogithub/1-3-cloud-adoption-skills/dsv4-c64-1280tps-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,145 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.03145
Opus 5 $0.00046 $0.01572
Sonnet 5 $0.00019 $0.00629
Haiku 4.5 $0.00009 $0.00314

Measured 11d ago against content hash b2e2713054b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dsv4-c64-1280tps-ascend-a3 scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/aggregate-results.py, scripts/dspark-serve-final.sh, scripts/dspark-serve-param.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://<inference-ip>:6697/health # expect 200
AI/AI-Infrastructure/dsv4-c64-1280tps-skill/SKILL.md · 268 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 268 lines · 93 tokens per session scan A b2e2713054b7

Subscribe to this mod's changes

dsv4-c64-1280tps-ascend-a3 is a skill published in the GitHub repository binrogithub/1-3-Cloud-Adoption-Skills (11 stars, last pushed today), with no licence file. It adds 93 tokens to every session and 3,145 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens