Search: throughput
29 result(s) on page 1
Model_Throughput_Tester
Automation skill for Model Throughput Tester.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Model_Throughput_TesterTax_Prep_—_Season_Throughput_(Theory_of_Constraints)
Activate when: returns are piling up before a deadline; reviewer/preparer is the bottleneck; 'we can't get through them all,' 'clients waiting on missing doc...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Tax_Prep_—_Season_Throughput_(Theory_of_Constraints)data-throughput-accelerator
Indexed by skills.sh from affaan-m/everything-claude-code
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.5
- Author
- affaan-m
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__data-throughput-acceleratorserving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.
quarantinedlinuxmacosvLLMoptional- Registry
- optional
- Category
- MLOps
- Version
- 1.0.0
- Author
- Orchestra Research
- License
- MIT
curl -s /v1/skills/community__axehub:optional__optional__serving-llms-vllmtensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
quarantinedlinuxmacosInference Servingoptional- Registry
- optional
- Category
- MLOps
- Version
- 1.0.0
- Author
- Orchestra Research
- License
- MIT
curl -s /v1/skills/community__axehub:optional__optional__tensorrt-llmAgent_Observability_-_Open_the_Black_Box
Provides full observability for OpenClaw agents via dashboards, decision logs, failure traces, and weekly compliance scoring for effective monitoring and deb...
quarantinedagent-debugagent-monitoringagent-qualityClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Observability_-_Open_the_Black_BoxReeflux_-_Agent_Habitat
A persistent habitat for autonomous agents focusing on stable memory, coordination, and iterative outcome optimization through collaborative pools.
quarantinedagentscoordinationdiscoveryClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Reeflux_-_Agent_Habitatstreaming-async
verifiedFirst-party- Registry
- First-party
- Category
- General
- Version
- 1.0.0
- Author
- AXE
- License
- MIT
curl -s /v1/skills/streaming-asyncAPI_Benchmark
Benchmark token generation speed across multiple LLM API providers. Measures TTFT (Time To First Token), tokens-per-second throughput, and total generation t...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__API_BenchmarkAgent_Conductor
Orchestrate coding sub-agents (Claude Code, Codex, Cursor, Gemini Code, or any CLI-based coding agent) for maximum throughput on implementation tasks. Use wh...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_ConductorAgent_Orchestration_Multi_Agent_Optimize
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Orchestration_Multi_Agent_OptimizeAgent_Synthesizer
Enable and configure Agent Synthesizer for OpenClaw to improve autonomy and execution throughput. Use when a user asks to install, set up, troubleshoot, or o...
quarantinedClawHub- Registry
- ClawHub
- Category
- Software Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_SynthesizerAgile_Observer
Proactive agile metrics and team health analysis for Trello and Jira boards. Computes cycle time, throughput, WIP, sprint burndown, aging work items, and blo...
quarantinedClawHub- Registry
- ClawHub
- Category
- Autonomous Ai Agents· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agile_ObserverConveyor
Conveyor system reference — belt types, motor sizing, throughput calculations, and material handling automation. Use when designing conveyor layouts, selecti...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ConveyorElixir_Performance_Review
Reviews Elixir code for performance issues including GenServer bottlenecks, memory usage, and concurrency patterns. Use when reviewing high-throughput code o...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Elixir_Performance_ReviewGo_Concurrency_Web
Go concurrency patterns for high-throughput web applications including worker pools, rate limiting, race detection, and safe shared state management. Use whe...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Go_Concurrency_WebHormuz_Strait_Monitor
Track shipping transit data through the Strait of Hormuz. Monitors transits, daily throughput, and non-Iranian vessel counts from hormuzstraitmonitor.com and...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Hormuz_Strait_MonitorOpenClaw_Benchmark
Measures OpenClaw model performance by scoring token throughput, first-token latency, tool call speed, context efficiency, and error recovery ability.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__OpenClaw_BenchmarkPerftest
Run HTTP performance tests with latency and throughput measurement. Use when benchmarking web services. Requires curl.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__PerftestPget
Parallel file download and optional tar extraction using the pget CLI (single URL or multifile manifest). Use when you need high‑throughput downloads from HTTP(S)/S3/GCS, want to split a large file into chunks for speed, or want to download and extract a .tar/.tar.gz in one step.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__PgetSglang_Amd_Bench
Benchmark sglang serving performance on AMD Instinct GPUs (MI355X, MI300X, MI308X) with various parallel configurations (TP, DP, EP). Covers throughput/laten...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Sglang_Amd_BenchTheory_of_Constraints
Activate when: user says 'everyone is working hard but results are flat', 'where is our bottleneck', 'we keep adding capacity but throughput doesn't improve'...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Theory_of_Constraintsdoca-bench
Use this skill when the user is running `doca_bench` (DOCA ≥ 2.7.0) — the cross-library micro-benchmark harness — to measure throughput, bulk-latency, precision-latency, or max-bandwidth (the four `benchmark_mode` enum values the binary ships) of a DOCA library (RDMA, COMPRESS…
quarantinedClawHub- Registry
- ClawHub
- Category
- Networking· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__doca-benchnemo-mbridge-perf-moe-hardware-configs
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
quarantinedClawHub- Registry
- ClawHub
- Category
- Training Ai· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__nemo-mbridge-perf-moe-hardware-configsrag-eval
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__rag-evaldoca-bench
Use this skill when the user is running `doca_bench` (DOCA ≥ 2.7.0) — the cross-library micro-benchmark harness — to measure throughput, bulk-latency, precision-latency, or max-bandwidth (the four `benchmark_mode` enum values the binary ships) of a DOCA library (RDMA, COMPRESS…
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- Networking
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__doca-benchnemo-mbridge-perf-moe-hardware-configs
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- Training AI
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__nemo-mbridge-perf-moe-hardware-configsrag-eval
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- Agentic AI
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__rag-evalcompare-and-build-llm-model
Search and compare OpenRouter's 350+ LLMs by cost, speed (throughput/latency/uptime), context length, modalities, and use-case category; pick the best fit; then build with it via OpenAI-compatible chat completions. API-first — no scraping, no auth for reads.
quarantinedllmopenroutermodel-selectionbrowse.sh- Registry
- browse.sh
- Category
- Ai Models
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:browse.sh__browse.sh__compare-and-build-llm-model