Agent skill · data analytics · jeremylongshore
coreweave-performance-tuning
Optimize CoreWeave GPU inference latency and throughput.
Why this skill is useful
Provides specific YAML configurations and performance benchmarks for optimizing GPU inference on CoreWeave that the AI wouldn't reliably generate on its own.
What it needs
Requires kubectl installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
CoreWeave Performance Tuning Community-contributed. Not affiliated with, endorsed by, or sponsored by CoreWeave, Inc. CoreWeave is a registered trademark of CoreWeave, Inc. Overview Tune GPU inference or training only against measured throughput, latency, quality, availability, and cost targets. A higher utilization figure is not a success if it causes queueing, memory pressure, or a customer-facing SLO regression. Prerequisites A baseline for p95/p99 latency, throughput, error rate, GPU memory, and utilization. A representative non-sensitive evaluation set and a named owner for the SLO. A staging lane and a rollback manifest for every resource or serving change. Instructions 1. Change one variable at a time—batching, GPU class, replicas, or memory target. 2. Run the agreed load and quality evaluation in staging, then compare with baseline. 3. Promote a canary only when all SLO and quality thresholds pass for the observation window. 4. Revert to the prior manifest when latency, errors, or quality crosses the agreed limit. GPU Selection by Workload Workload Recommended GPU Why ---------- ---------------- ----- LLM inference (7-13B) A100 80GB Good balance of memory and cost LLM inference (70B+) 8xH100 NVLink for tensor parallelism Image generation L40 Good for diffusion models Training (large models) 8xH100 SXM5 Fastest interconnect Batch processing A100 40GB Cost-effective Inference Optimization Autoscaling Tuning Performance Benchmarks Metric A100-80GB H100-80GB -------- ----------- ----------- Llama-8B tokens/sec ~2,000 ~4,500 Llama-70B tokens/sec ~200 (4x) ~500 (4x) Cold start (vLLM) 30-60s 20-40s Output A measured performance baseline and a single reviewed tuning recommendation. A canary result covering throughput, latency, error rate, GPU memory, and quality. A versioned rollback manifest with a named decision owner. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/coreweave-performance-tuning