Query GPU optimization knowledge and hardware facts through the session's Supervisor Runtime.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
In every natural-language Wiki request, state the true target product separately from the authoritative runtime architecture; never infer either from a scheduler label or masked device name. If the true product is unavailable, say so rather than substitute another GPU. Ask for that product's hardware specification and relevant architecture/ISA facts alongside the operator, DSL and bottleneck. Distinguish measurements from hypotheses. Do not reduce the question to arbitrary keywords.
python3 tools/sandbox.py --kind wiki-query "Target B200, runtime sm_100. Triton normalization is measured DRAM-bound; which fusion strategies apply? Include B200 hardware specifications and relevant architecture/ISA facts." --brief
python3 tools/sandbox.py --kind wiki-query --file scratch/wiki-question.txt
python3 tools/sandbox.py --kind wiki-search --arch sm_120 --dsl triton --coverage
python3 tools/sandbox.py --kind wiki-hardware --product sm120
Use the tools/sandbox.py --kind wiki-* commands above from an Agent workspace.
The Supervisor owns stores, the Wiki-only model, timeouts, concurrency and query
telemetry; never override their host paths or provider configuration. Repeating an
identical query in this Episode reuses the same completed response and query_id.
For repairable: true with error.code: "request_not_started", wait at least
retry_after_seconds before retrying the unchanged query with backoff. The query
executor has not started. Do not blindly retry transport failures or unknown outcomes.
For wiki_queue_timeout, wiki_query_in_progress, wiki_query_timeout or
wiki_unavailable, wait at least retry_after_seconds and retry the same read-only
query unchanged. Do not submit parallel copies or wrap the call in a shorter shell
timeout. If Wiki remains unavailable, continue with other tools and report the
blocker. A Wiki failure is not a GPU environment failure.
Check coverage before restrictive type filters. Read the returned source, scope,
payload and notes. A zero-match fallback sample is labelled, not advice for your
question. A missing hardware spec is not permission to substitute another GPU.
When research recording is enabled, record query_id and canonical wiki_id in the existing
Experiment Journal when knowledge materially affects an experiment; retrieval alone is not adoption.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Prepare requests for the selected AKA Execution entry point, consult Gateway or SSH guidance, and preserve complete execution output and artifacts. Use for handing prepared GPU commands, evaluation, or profiling work to AKA Execution; experiment planning and result interpretation belong to their callers.
中文简介正在准备中。当前显示原文说明。
Use the selected reliable GPU executor from the legacy Workflow.
中文简介正在准备中。当前显示原文说明。
Let AKA autonomously add, run, inspect, and revise intra-kernel timeline probes for standalone CUDA/inline PTX or CuTe DSL when ordinary benchmark, NSYS, or NCU evidence cannot answer a specific kernel-internal timing question.
中文简介正在准备中。当前显示原文说明。
Generate a structured implementation plan from an evidence draft. Validate paths, obtain configured independent Codex and Qoder reviews, synthesize available advice against repository evidence, preserve the draft, and produce testable acceptance criteria and validation steps.
中文简介正在准备中。当前显示原文说明。
Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel. Use this skill to understand compute semantics, determine the target platform and framework, search reference implementations, and produce a correct V0 baseline with performance records for later profile-driven optimization.
中文简介正在准备中。当前显示原文说明。
Run the evidence loop of one long-horizon GPU kernel optimization episode. Use this skill to reconstruct the incumbent, profile and localize a bottleneck, research progressively, plan one coherent direction, implement and repair, validate development correctness and performance, and record every decisive experiment in the episode journal.
中文简介正在准备中。当前显示原文说明。