Use the selected reliable GPU executor from the legacy Workflow.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
For prepared host commands, use the selected aka execution --profile reliable entry point and its --help request format. The selected controller executor retains request checkpoints and known remote job IDs outside the Agent workspace. Retries apply only to confirmed admission/transport failures. An unknown submission outcome must be reconciled by the operator, not blindly resubmitted. An Eval execution timeout is a candidate failure, not an environment outage. Do not switch a failed Eval to Dev.
This selection does not replace a legacy Agent's direct tools/sandbox.py, or install the light HTTP ToolHost or Journal. The light Workflow separately provides its authenticated HTTP client and the gpu-measurement and runtime-records Skills. Do not assume that loading this Skill changes every tool's transport.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run Kernel evaluation, ABBA comparison, profiling and GPU probes through the session's Supervisor HTTP Runtime.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.