triton-ascend-memory

triton-ascend-memory is a skill for Claude Code, Codex from mindspore-ai/akg. It costs 68 tokens per session (697 once invoked), scanned A, original, Apache-2.0.

A guide to improving memory access in Triton kernels for Ascend hardware. It covers temporary buffer use, block sizes, aligned transfers, contiguous data, 2D block pointers, and prefetching.

In plain words
What is it for?
Use it when tuning element-wise, reduction, softmax, matrix, or other kernels whose speed depends on moving data efficiently.
Why use it?
It helps address slow kernels or memory overflow caused by unsuitable block sizes, unaligned transfers, or inefficient access to non-contiguous tensors.

Skill for Claude CodeCodex

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

Good fit Use it when tuning element-wise, reduction, softmax, matrix, or other kernels whose speed depends on moving data efficiently.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mindspore-ai/akg/triton-ascend-memory
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-memory
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-memory

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-memory"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-memory.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 697 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 $0.00697
Opus 5 $0.00034 $0.00349
Sonnet 5 $0.00014 $0.00139
Haiku 4.5 $0.00007 $0.00070

Measured 9d ago against content hash 97696bd43dab, 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-memory 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-memory/SKILL.md · 63 lines

What it actually says

内存访问优化

块大小选择原理

块大小需要根据算子类型和硬件存储层级来平衡:

  • VEC 类算子(element-wise、reduce、softmax 等):数据需放入 UB(192KB/VEC),BLOCK_SIZE * sizeof(dtype) 需小于 UB 可用容量,同时兼顾计算并行度。过小并行度不足,过大溢出 UB
  • CUBE 类算子(matmul、attention 等):左矩阵放 L0A(* KB),右矩阵放 L0B(* KB),结果放 L0C(* KB),具体参考硬件信息文档:
    • m0 * k0 * sizeof(A.dtype) ≤ * KB(L0A)
    • k0 * n0 * sizeof(B.dtype) ≤ * KB(L0B)
    • m0 * n0 * sizeof(C.dtype) ≤ * KB(L0C)
  • 所有数据传输按 256 Bytes 对齐,BLOCK_SIZE 为 32 的倍数最优

2D 数据:优先 tl.make_block_ptr

A_block_ptr = tl.make_block_ptr(
    base=A_ptr, shape=(M, K), strides=(stride_am, stride_ak),
    offsets=(pid_m * BLOCK_M, 0), block_shape=(BLOCK_M, BLOCK_K), order=(1, 0),
)
a = tl.load(A_block_ptr, boundary_check=(0, 1))
# 移动指针
A_block_ptr = tl.advance(A_block_ptr, (0, BLOCK_K))

连续内存:一维访问

非连续张量先 .contiguous() 转换,再用一维 ptr + offsets 访问:

class ModelNew(torch.nn.Module):
    def forward(self, x):
        if not x.is_contiguous():
            x = x.contiguous()
        out = torch.empty_like(x)
        n = x.numel()
        grid = (triton.cdiv(n, BLOCK_SIZE),)
        kernel[grid](x, out, n, BLOCK_SIZE=1024)
        return out

一维访问比 stride 计算效率更高,推荐优先使用。

对齐要求

  • Ascend 256B 对齐: element-wise / reduce 算子
  • Ascend 512B 对齐: MatMul 切分
  • 数据搬运带宽上限约 256*256B,据此设计搬运策略

要点

  • 优先 .contiguous() + 一维访问
  • 连续内存访问效率远高于 stride 计算开销
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 · 63 lines · 68 tokens per session scan A 97696bd43dab

Subscribe to this mod's changes

triton-ascend-memory 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 697 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