vllm-mindspore-post-process

vllm-mindspore-post-process is a skill for OpenCode from mindspore-ai/akg. It costs 32 tokens per session (1,893 once invoked), scanned A, original, Apache-2.0.

A guide to speeding up the processing that happens after vLLM-MindSpore produces model results and before it selects the next tokens. vLLM-MindSpore is a text-generation system adapted for Huawei Ascend hardware.

In plain words
What is it for?
It is for improving post-processing through caching, parallel work, vector operations, and processing only the values needed.
Why use it?
It helps reduce unnecessary work in penalty calculations, temperature changes, and token filtering during text generation.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

Good fit It is for improving post-processing through caching, parallel work, vector operations, and processing only the values needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mindspore-ai/akg/vllm-mindspore-post-process
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 vllm-mindspore-post-process
Clone the repo
git clone --depth 1 https://github.com/mindspore-ai/akg

Made for: OpenCode.

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 vllm-mindspore-post-process

README.md
[![agentmods](https://agentmods.dev/badge/skills/mindspore-ai/akg/vllm-mindspore-post-process/github.svg)](https://agentmods.dev/skills/mindspore-ai/akg/vllm-mindspore-post-process)
Your own site
<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.

agentmods 80×15 button for vllm-mindspore-post-process

Your own site · 80×15
<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>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,893 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 $0.00032 $0.01893
Opus 5 $0.00016 $0.00946
Sonnet 5 $0.00006 $0.00379
Haiku 4.5 $0.00003 $0.00189

Measured 9d ago against content hash fbd90dbeb7e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

akg_agents/workspace/.opencode/skills/vllm-mindspore-post-process/SKILL.md · 179 lines

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

Read the full file on GitHub · 179 lines

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 · 179 lines · 32 tokens per session scan A fbd90dbeb7e5

Subscribe to this mod's changes

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.

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