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.
npx skills add mindspore-ai/akg --skill triton-ascend-basicsgit clone --depth 1 https://github.com/mindspore-ai/akgWrote 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.
[](https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-basics)<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-basics"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-basics/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.
<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-basics"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-basics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.01522 |
| Opus 5 | $0.00033 | $0.00761 |
| Sonnet 5 | $0.00013 | $0.00304 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
triton-ascend-basics 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triton Ascend 编程基础
标准内核结构(交错循环)
@triton.jit
def kernel(
output_ptr, input_ptr, n_elements,
BLOCK_SIZE: tl.constexpr, CORE_NUM: tl.constexpr,
):
pid = tl.program_id(0)
num_blocks = tl.cdiv(n_elements, BLOCK_SIZE)
for block_id in range(pid, num_blocks, CORE_NUM):
offsets = block_id * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
mask = offsets < n_elements
data = tl.load(input_ptr + offsets, mask=mask, other=0.0)
result = compute(data)
tl.store(output_ptr + offsets, result, mask=mask)
内核启动模板
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)
except:
self.VEC_CORE_NUM = 40
def forward(self, x):
out = torch.empty_like(x)
BLOCK_SIZE = 1024
grid = (self.VEC_CORE_NUM,) # Ascend: 固定为核心数
kernel[grid](out, x, x.numel(), BLOCK_SIZE=BLOCK_SIZE, CORE_NUM=self.VEC_CORE_NUM)
return out
边界处理
offsets = block_id * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
mask = offsets < n_elements
data = tl.load(ptr + offsets, mask=mask, other=0.0)
result = tl.where(condition, true_val, false_val)
Autotune 用法(仅限静态 shape)
Autotune 通过自动 benchmark 多组配置参数,找到当前硬件和数据规模下的最优配置并缓存,免去手动调参。
适用场景
- 推荐使用:输入 shape 固定或变化范围有限(静态 shape),如固定 batch size 的 MatMul、固定序列长度的 Attention 等
- 禁止使用:输入 shape 频繁变化(动态 shape)。autotune 根据
key参数缓存最佳 config,动态 shape 下每组新 shape 都会触发一次完整 benchmark,反而严重拖慢性能
强制规则
- 必须写
restore_value:列出 kernel 的所有输出指针参数名。autotune benchmark 会对每个 config 反复执行 kernel,restore_value在每次迭代前保存输出张量副本、迭代后恢复原值,防止不同 config 之间的结果互相污染。不写restore_value会导致验证失败。 - 调用时不传 configs 参数:autotune 自动传入。
- configs 参数必须是 constexpr:在 kernel 中声明为
PARAM: tl.constexpr。 - key 参数:指定哪些输入维度变化时重新 autotune。
- Ascend 不支持调优:不要对 num_warps、num_ctas、num_stages 等参数进行修改调优,当前 Ascend 后端不支持。
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.
- 9d ago First seen · 143 lines · 66 tokens per session scan A af849fedde4a
triton-ascend-basics is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,522 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.
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.
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.
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.
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.
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.
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"…