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 vllm-ascend-post-processgit 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/vllm-ascend-post-process)<a href="https://agentmods.dev/skills/mindspore-ai/akg/vllm-ascend-post-process"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/vllm-ascend-post-process/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/vllm-ascend-post-process"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/vllm-ascend-post-process.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 | $0.00039 | $0.01904 |
| Opus 5 | $0.00019 | $0.00952 |
| Sonnet 5 | $0.00008 | $0.00381 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
vllm-ascend-post-process 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vllm-ascend 后处理优化 Skill
背景知识
vllm-ascend 是基于 vllm 二次开发适配 ASCEND (华为昇腾) 的推理框架，使用 PyTorch + NPU 后端，后处理使用 Triton 自定义算子 实现。
vllm-ascend 有两套采样架构:
- V1: 基于 PyTorch 实现，使用 NPU 算子加速
- V2: 基于 Triton 自定义算子实现，针对 NPU 优化
| Rule | Value |
|---|---|
| 采样架构 | V1 (PyTorch+NPU) / V2 (Triton) |
| 核心文件 | vllm_ascend/worker/v2/sample/ |
| 优化重点 | Triton Kernel、NPU算子、惩罚计算、Gumbel采样 |
vllm-ascend 后处理流程架构
文件路径 | 作用 | 关键函数
vllm_ascend/worker/v2/sample/sampler.py | V2采样主入口 | AscendSampler.sample()
vllm_ascend/worker/v2/sample/penalties.py | 核心后处理-惩罚计算 | apply_penalties_and_temperature(), _penalties_and_temperature_kernel (Triton)
vllm_ascend/worker/v2/sample/gumbel.py | Gumbel采样 | gumbel_sample(), _gumbel_sample_kernel (Triton)
vllm_ascend/sample/sampler.py | V1采样实现 | AscendSampler, AscendTopKTopPSampler
csrc/apply_top_k_topp_custom/ | Top-K/Top-P 自定义算子 | NPU融合算子实现
后处理流程详解 (V2架构)
模型输出 Logits
│
▼
┌─────────────────────────────────────────┐
│ 1. 惩罚计算 (penalties.py) │
│ - Repetition Penalty (重复惩罚) │
│ - Frequency Penalty (频率惩罚) │
│ - Presence Penalty (存在惩罚) │
│ - Temperature (温度调节) │
│ - Triton Kernel: _penalties_and_temperature_kernel
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 2. Min-P 过滤 (sampler.py) │
│ - apply_min_p() │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 3. Top-K/Top-P 过滤 (sampler.py) │
│ - apply_top_k_top_p() │
│ - NPU融合算子 / PyTorch原生 │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 4. Gumbel采样 (gumbel.py) │
│ - _gumbel_sample_kernel (Triton) │
└─────────────────────────────────────────┘
│
▼
采样结果
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 · 182 lines · 39 tokens per session scan A fe03cd272b4b
vllm-ascend-post-process is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,904 once invoked, about $0.0002 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"…