triton-ascend-grid-config

triton-ascend-grid-config is a skill for Claude Code, Codex from mindspore-ai/akg. It costs 68 tokens per session (803 once invoked), scanned A, original, Apache-2.0.

A guide to choosing the grid and block settings that divide Triton work across Ascend processor cores. A grid describes the launched work, while a block is one portion of the data handled by that work.

In plain words
What is it for?
Use it when generating kernels for element-wise operations, reductions, normalization, or large shapes, including code that needs vector and matrix core counts.
Why use it?
It helps avoid invalid launch configurations and poor parallel use when processing large tensors or choosing how many cores should work at once.

Skill for Claude CodeCodex

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

Good fit Use it when generating kernels for element-wise operations, reductions, normalization, or large shapes, including code that needs vector and matrix core counts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mindspore-ai/akg/triton-ascend-grid-config
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 mindspore-ai/akg --skill triton-ascend-grid-config
Clone the repo
git clone --depth 1 https://github.com/mindspore-ai/akg

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 triton-ascend-grid-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-grid-config/github.svg)](https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-grid-config)
Your own site
<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-grid-config"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-grid-config/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 triton-ascend-grid-config

Your own site · 80×15
<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-grid-config"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-grid-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00068 $0.00803
Opus 5 $0.00034 $0.00402
Sonnet 5 $0.00014 $0.00161
Haiku 4.5 $0.00007 $0.00080

Measured 9d ago against content hash c8cef7a83081, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

triton-ascend-grid-config scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

akg_agents/python/akg_agents/op/resources/skills/triton-ascend/fundamentals/triton-ascend-grid-config/SKILL.md · 83 lines

What it actually says

Grid 配置策略

Grid 限制

  • Grid 必须是 tuple,最多 3 维:(x,), (x, y), (x, y, z)
  • 各维度乘积不超过 65535
  • BLOCK_SIZE 必须小于 65536

推荐方案:交错循环(固定 Grid 为核心数)

适用于按行/按块独立处理的算子(Element-wise、Reduce、Normalization 等)。

@triton.jit
def kernel(
    input_ptr, output_ptr, M, N,
    stride_m, stride_n,
    BLOCK_N: tl.constexpr,
    CORE_NUM: tl.constexpr,
):
    pid = tl.program_id(0)
    # 交错处理:pid=0 处理第 0, CORE_NUM, 2*CORE_NUM, ... 行
    for row_idx in range(pid, M, CORE_NUM):
        row_ptr = input_ptr + row_idx * stride_m
        out_ptr = output_ptr + row_idx * stride_m
        for col_start in range(0, N, BLOCK_N):
            offs = col_start + tl.arange(0, BLOCK_N)
            mask = offs < N
            data = tl.load(row_ptr + offs * stride_n, mask=mask)
            result = compute(data)
            tl.store(out_ptr + offs * stride_n, result, mask=mask)

动态获取核心数

必须在 __init__ 中获取,禁止在 forward 中调用(触发设备同步)。

import torch_npu

class ModelNew(torch.nn.Module):
    def __init__(self):
        super().__init__()
        try:
            self.VEC_CORE_NUM = torch_npu.npu.npu_config.get_device_limit(0).get("vector_core_num", 40)
            self.CUBE_CORE_NUM = torch_npu.npu.npu_config.get_device_limit(0).get("cube_core_num", 20)
        except:
            self.VEC_CORE_NUM = 40
            self.CUBE_CORE_NUM = 20

    def forward(self, x):
        M, N = x.shape
        out = torch.empty_like(x)
        grid = (self.VEC_CORE_NUM,)
        kernel[grid](x, out, M, N, x.stride(0), x.stride(1),
                     BLOCK_N=256, CORE_NUM=self.VEC_CORE_NUM)
        return out

核心数选择

  • 向量算子(element-wise、softmax、归一化):使用 VEC_CORE_NUM
  • 矩阵算子(matmul、attention):使用 CUBE_CORE_NUM

多次切分策略

若 BLOCK_SIZE 超限或单次切分超硬件缓存,可嵌套循环做多层切分:

for m_start in range(pid_m * BLOCK_M, min((pid_m + 1) * BLOCK_M, M), SUB_BLOCK_M):
    for n_start in range(pid_n * BLOCK_N, min((pid_n + 1) * BLOCK_N, N), SUB_BLOCK_N):
        # 处理 SUB_BLOCK 大小的子块
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. 9d ago First seen · 83 lines · 68 tokens per session scan A c8cef7a83081

Subscribe to this mod's changes

triton-ascend-grid-config is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 803 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

minicpm5-deploy-vllm-ascend

Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.

OpenBMB/MiniCPM · 87 tokens

minicpm5-deploy-litert

Run MiniCPM5-2B or MiniCPM5-1B on-device with Google's LiteRT-LM runtime — the litert-lm CLI or its OpenAI-compatible server on a desktop, the Kotlin API or the AI Edge Gallery app on Android, the same .litertlm bundle on CPU or GPU. Use when the user says "LiteRT", "LiteRT-LM", "litertlm", ".litertlm", "Android"…

OpenBMB/MiniCPM · 121 tokens