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-mindspore-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-mindspore-post-process)<a href="https://agentmods.dev/skills/mindspore-ai/akg/vllm-mindspore-post-process"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/vllm-mindspore-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-mindspore-post-process"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/vllm-mindspore-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 | $0.00032 | $0.01893 |
| Opus 5 | $0.00016 | $0.00946 |
| Sonnet 5 | $0.00006 | $0.00379 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
vllm-mindspore-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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vllm-mindspore 后处理优化 Skill
背景知识
vllm-mindspore 是基于 vllm 二次开发适配 ASCEND (华为昇腾) 的推理框架。其后处理流程位于模型推理 (Forward) 之后、采样 (Sampling) 之前的阶段。
| Rule | Value |
|---|---|
| 核心文件 | vllm_mindspore/v1/ |
| 优化重点 | 惩罚计算、温度调节、Top-K/Top-P 过滤 |
| 优化模式 | 按需计算、范围缩减、索引传递、短路返回 |
vllm-mindspore 后处理流程架构
文件路径 | 作用 | 关键函数
vllm_mindspore/v1/worker/gpu_input_batch.py | 采样参数准备 | _make_sampling_metadata()
vllm_mindspore/model_executor/layers/utils.py | 核心后处理-惩罚计算 | apply_penalties(), get_token_bin_counts_and_mask()
vllm_mindspore/v1/sample/sampler.py | 温度调节 | apply_temperature()
vllm_mindspore/v1/sample/ops/penalties.py | 惩罚张量转换 | _convert_to_tensors()
vllm_mindspore/v1/sample/ops/topk_topp_sampler.py | Top-K/Top-P过滤 | apply_top_k_top_p(), apply_top_k_only(), random_sample()
vllm_mindspore/v1/worker/gpu_model_runner.py | 模型推理执行 | execute_model()
后处理流程详解
模型输出 Logits
│
▼
┌─────────────────────────────────────────┐
│ 1. 惩罚计算 (apply_penalties) │
│ - Repetition Penalty (重复惩罚) │
│ - Frequency Penalty (频率惩罚) │
│ - Presence Penalty (存在惩罚) │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 2. 温度调节 (apply_temperature) │
│ - logits = logits.div(temp) │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 3. Top-K 过滤 (apply_top_k_only) │
│ - 只保留概率最高的 k 个 token │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 4. Top-P 过滤 (apply_top_k_top_p) │
│ - 保留概率累加和达到 p 的最小集合 │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ 5. 采样 (random_sample) │
│ - 基于处理后的概率分布进行采样 │
└─────────────────────────────────────────┘
│
▼
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 · 179 lines · 32 tokens per session scan A fbd90dbeb7e5
vllm-mindspore-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 32 tokens to every session and 1,893 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"…