ascend-inference-repos-copilot

ascend-inference-repos-copilot is a skill for Claude Code, Codex from Inference1/learn-agent-skills. It costs 353 tokens per session (5,325 once invoked), scanned A, original, MIT.

A Chinese-language question-and-answer guide for Ascend inference repositories, which are software projects for running machine-learning models on Huawei Ascend hardware. It covers vLLM, MindIE, and related projects with evidence-based technical answers.

In plain words
What is it for?
Use it to investigate repository behavior, deployment steps, and troubleshooting issues involving Ascend hardware and inference software.
Why use it?
It helps explain source code, architecture, setup, and failures where software versions, hardware models, and dependencies must match closely.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate repository behavior, deployment steps, and troubleshooting issues involving Ascend hardware and inference software.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/inference1/learn-agent-skills/ascend-inference-repos-copilot
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 Inference1/learn-agent-skills --skill ascend-inference-repos-copilot
Clone the repo
git clone --depth 1 https://github.com/Inference1/learn-agent-skills

Made for: Claude Code, Codex.

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 ascend-inference-repos-copilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/inference1/learn-agent-skills/ascend-inference-repos-copilot/github.svg)](https://agentmods.dev/skills/inference1/learn-agent-skills/ascend-inference-repos-copilot)
Your own site
<a href="https://agentmods.dev/skills/inference1/learn-agent-skills/ascend-inference-repos-copilot"><img src="https://agentmods.dev/badge/skills/inference1/learn-agent-skills/ascend-inference-repos-copilot/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 ascend-inference-repos-copilot

Your own site · 80×15
<a href="https://agentmods.dev/skills/inference1/learn-agent-skills/ascend-inference-repos-copilot"><img src="https://agentmods.dev/badge/skills/inference1/learn-agent-skills/ascend-inference-repos-copilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 353 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,325 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 original 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 $0.00353 $0.05325
Opus 5 $0.00177 $0.02662
Sonnet 5 $0.00071 $0.01065
Haiku 4.5 $0.00035 $0.00532

Measured 11d ago against content hash 9b384e6f1bc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ascend-inference-repos-copilot 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.

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.

- **GitCode Issues** (for `verylucky01/*` repos — replace `verylucky01` with `Ascend` in the API path): `curl --location 'https://api.gitcode.com/api/v5/search/issues?q=<keywords>&repo=<Ascend/repo>' --header 'Authorizat
skills/ascend-inference-repos-copilot/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specialized Intelligent Q&A for Ascend Inference Open-Source Code Repositories

Answer technical questions about Ascend inference repositories with evidence-based, causally-grounded responses. DeepWiki is the primary knowledge source; embedded knowledge below is orientation context to help formulate better queries.

Quick Diagnostic (for error/troubleshooting questions)

Before diving into deep research, complete this checklist — it resolves ~60% of issues and takes 2 minutes. Do not skip steps in favor of going straight to GitHub Issues.

  1. Version alignment — vllm-ascend requires strict 1:1 match with upstream vLLM (e.g., v0.18.0 ↔ v0.18.0). Each release also pins exact CANN and torch_npu versions. Misalignment is the #1 root cause.
  2. Isolate graph mode — add --enforce-eager to rule out ACLGraph/torchair as the cause.
  3. Check the error code — ACL error codes point directly to the failure layer: 507015 (stream sync), 561000 (MoE dispatch), 503900 (KV transfer).
  4. Hardware platform — 310P (Atlas 300I Duo) has a significantly smaller operator library than 910B. Features that work on 910B may simply not exist on 310P.
  5. Feature combination — MTP + FULL_DECODE_ONLY, NZ layout + RL training, and W8A8 + MTP are known incompatible combinations.
  6. max_model_len — silently too-large values cause OOM, garbled output, and shape errors. Always verify or suggest reducing it.
  7. Enable synchronous error reporting — async execution hides the real error. Set these before reproducing:
    export ASCEND_LAUNCH_BLOCKING=1   # synchronous NPU execution — accurate stack traces
    export TASK_QUEUE_ENABLE=0        # disables async task queue
    export ASCEND_GLOBAL_LOG_LEVEL=0  # verbose CANN logs
    

Ask for python collect_env.py output (from the vllm-ascend repo root) when you need version details. Key fields to check: vllm_ascend, vllm, torch_npu, CANN, driver.

Research strategy: Complete the Quick Diagnostic checklist first, then use GitHub Issues search for version-specific bugs or recent fixes. Deep research should supplement standard checks, not replace them.

Read the full file on GitHub · 228 lines

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 · 228 lines · 353 tokens per session scan A 9b384e6f1bc5

Subscribe to this mod's changes

ascend-inference-repos-copilot is a skill published in the GitHub repository Inference1/learn-agent-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 353 tokens to every session and 5,325 once invoked, about $0.0018 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 2026-08-31.

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