Agent Claude Code
Path C Phase 2 subagent. Probe or install AISBench from source in a target container before PD deploy. Skip if already available. Writes aisbench-install-report/status.
not rated 2 1mo ago A 44 tokens
Agent Claude Code
A specialised agent for reproducing serving-performance baselines for a model-serving setup. It uses configuration files and reference documents to produce a usable vLLM server command when needed.
not rated 2 1mo ago A 85 tokens
Agent Claude Code
Path C Phase 1 subagent. Validate PD Prefill/Decode launch commands and machine/container environment; ensure one container per host when unspecified; network-only multi-host rewrites; write pd-check-report and rendered scripts.
not rated 2 1mo ago A 53 tokens
Agent Claude Code
Path C Phase 3 subagent. Deploy mooncakemaster then Prefill/Decode/Proxy from Phase 1 rendered scripts after AISBench is ready; on failure diagnose and signal rollback to Phase 1.
not rated 2 1mo ago A 51 tokens
Agent Claude Code
Path C Phase 4 subagent. Run AISBench P/D QPS tests under SLO, compute best PD ratio, fit to cluster capacity, verify deploy + e2e per-NPU throughput; write pd-ratio-report and status. P checks TTFT only; D checks TPOT only; concurrencies may differ.
not rated 2 1mo ago A 77 tokens
Agent Claude Code
A specialized helper for analyzing performance profiles from Ascend NPU tools, using local paths to profiling files such as ascendpt, ascendms, or PROF data.
not rated 2 1mo ago A 106 tokens
Agent Claude Code
A specialized agent for the second phase of serving-performance tuning, starting from a Phase 1 baseline summary. The description is in Chinese and says it performs offline parallel-strategy tuning without deployment or load testing.
not rated 2 1mo ago A 86 tokens
Skill Claude CodeCodex
Probe or install AISBench from source inside a target container for Path C PD-ratio benchmarking. Runs after pd-config-env-check and before pd-deploy. Skip if aisbench is already available. Pin numpy for vLLM Ascend co-install.
not rated 2 1mo ago A 55 tokens
Skill Claude CodeCodex
Finds the best vLLM-Ascend deployment config (low-latency or high-throughput) from local baseline markdown docs by matching device, model, quantization, NPU count, and deploy strategy; if no local match, fetches high-throughput configs from the official vLLM-Ascend model tutorials. Adjusts context length by…
not rated 2 1mo ago A 116 tokens
Skill Claude CodeCodex
A diagnostic skill for finding fast and slow devices in Ascend cluster profiling data, where a cluster is a group of computers or accelerators working together.
not rated 2 1mo ago A 127 tokens
Skill Codex
Analyze Ascend NPU collective communication profiling data with a DB-first workflow. Use when the user provides clusteranalysisoutput/clusteranalysis.db, rank-level analysis.db, rank-level ascendpytorchprofiler{rankid}.db, together with profilerinfo.json, and asks about HCCL or hcom communication cost, collective…
not rated 2 1mo ago A 119 tokens
Skill Claude CodeCodex
Analyze Ascend NPU computation-side profiling data for single-card runs or a selected rank from multi-card runs. Use this skill when the user asks to diagnose computation bottlenecks, AI Core / AI Vector / AICPU hotspots, dynamic shape overhead, block dim issues, redundant TransData/Transpose/Cast, cross-stream waits…
not rated 2 1mo ago A 82 tokens
Skill Claude CodeCodex
A tool for collecting, analyzing, and comparing information from Ascend NPU environments and dump files.
not rated 2 1mo ago A 55 tokens
Skill Claude CodeCodex
A command-line analysis tool for profiling data from AI training and inference. Profiling data records how a program spends time and resources while it runs.
not rated 2 1mo ago A 72 tokens
Skill Claude CodeCodex
A validation guide for performance data collected by MindStudio profiler tools. Profiling records how software uses time and resources so performance problems can be studied.
not rated 2 1mo ago A 56 tokens
Skill Claude CodeCodex
A SQL analysis skill for Ascend PyTorch Profiler and msprof database files. It turns questions about operator timing, communication, scheduling, or database tables into safe SQL queries and can look up official schema details.
not rated 2 1mo ago A 82 tokens
Skill Claude CodeCodex
Analyze Ascend NPU schedule, operator dispatch, operator launch, and Host Bound profiling issues in Ascend profiling data. Use when need to diagnose device Free time, framework/operator dispatch latency, launch latency, PYTORCHAPI/CANNAPI launch gaps, aclrtSynchronizeStream stalls, task queue behavior, CPU scheduling…
not rated 2 1mo ago A 86 tokens
Skill Claude CodeCodex
Ascend cluster performance analysis and comparison tool. Invoke when user asks to analyze cluster profiling data (DB or TEXT format), generate cluster analysis reports, or compare two cluster datasets.
not rated 2 1mo ago A 38 tokens
Skill Claude CodeCodex
Parses msprof-analyze compare output xlsx, extracts key insights per sheet, generates HTML report and Chinese xlsx. Pipeline-only for Path B after ascend-msprof-analyze-cli; do not invoke as a standalone tool.
not rated 2 1mo ago A 50 tokens
Skill Claude CodeCodex
Enumerates legal DP×TP×EP parallel combinations for vLLM-Ascend single-node mixed deployment from model weight size and NPU count. Use when computing min TP, listing parallel strategy candidates, or as sub-skill of serving-parallel-strategy-tuning.
not rated 2 1mo ago A 63 tokens
Skill Claude CodeCodex
A helper for reading source code, configuration, README files, Markdown, and documentation from GitHub links or repositories.
not rated 2 1mo ago A 114 tokens
Skill Claude CodeCodex
Reads model feature support table (xlsx) and converts to compact JSON. Invoke when user needs to parse or convert model-feature xlsx to JSON, or query model feature support across versions.
not rated 2 1mo ago A 42 tokens
Skill Claude CodeCodex
Installation and setup instructions for connecting msprof-mcp, a server that lets coding tools analyse Ascend performance-profile data, to tools such as Cursor or Claude Code.
not rated 2 1mo ago A 117 tokens
Skill Claude CodeCodex
A calculator for MFU, or Machine FLOP Utilization, which measures how much of a machine's theoretical calculation capacity an operation uses.
not rated 2 1mo ago A 38 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: