Skip to main content
cfregly
GitHub 제작자 프로필

cfregly

5개 GitHub 저장소에서 수집된 53개 skills를 저장소 단위로 보여줍니다.

수집된 skills
53
저장소
5
업데이트
2026년 8월 4일
저장소 탐색

저장소와 대표 skills

inference-capacity-sizing
소프트웨어 개발자

SLA-first GPU capacity sizing for a serving deployment: given a tokens-per-minute (TPM) target AND the interactivity SLA (output tokens/s/user), compute the pods and GPUs needed from a model's measured tok/s/user-vs-concurrency curve. Sizing MUST start from…

2026년 8월 4일
inference-decode-step-budget
소프트웨어 개발자

Measure the low-concurrency (c=1..c=8) decode hot-path of a live vLLM pod FAST and CORRECTLY: where each token's time actually goes (GPU-busy vs host-idle gap vs comm), whether the workload is kernel-bound / host-bound / comm-bound, and what the addressable…

2026년 8월 4일
inference-kernel-ncu-profile
소프트웨어 개발자

Capture per-kernel CUDA hardware-counter data (occupancy, achieved warps active, regs/thread, smem/block, DRAM throughput, arithmetic intensity, branch divergence %, warp-stall reason %) from a live vLLM inference pod via an `ncu` debug sidecar (no production…

2026년 8월 4일
inference-kernel-profile
소프트웨어 개발자

Capture per-kernel CUDA profile data from a live vLLM inference pod via an nsys debug sidecar (no production image rebuild). Outputs `.nsys-rep` + summary CSV + top-kernels table that joins with the zymtrace per-kernel breakdown and the inference-perf-bench…

2026년 8월 4일
inference-model-optimize
소프트웨어 개발자

End-to-end orchestrator that takes a NEW model from a bare HuggingFace id to a perf-lake-published, validated CROSS-ENGINE (vLLM + SGLang) champion on B200/GB300. Scaffolds a per-model harness + evidence bundle (run-id == experiment-id), then drives…

2026년 8월 4일
inference-perf-bench
소프트웨어 개발자

Canonical inference perf-bench skill (formal name. The colloquial alias is `ai-bench` - identical behaviour). Drives NVIDIA AIPerf + the replay-playback dataset against an in-cluster vLLM endpoint to measure TTFT, ITL, throughput, tok/s/user, request latency,…

2026년 8월 4일
inference-performance-hints
소프트웨어 개발자

Applies Jeff Dean and Sanjay Ghemawat's Performance Hints to GPU inference. Builds a back-of-the-envelope cost ledger, identifies the hot-path class, bounds each optimization with profile share, and routes the highest-value hypothesis to the repo's benchmark,…

2026년 8월 4일
inference-tune-sweep
소프트웨어 개발자

Search a vLLM serving model's config space for its best inference performance: a `perftunereport campaign_run` matrix sweep over concurrency x max_num_batched_tokens x kv-cache-dtype x cudagraph_mode, plus a same-node controlled A/B (`run-controlled-ab.sh`)…

2026년 8월 4일
수집된 skill 33개 중 8개를 표시합니다.
evidence-bundle-init
소프트웨어 개발자

Scaffold a new evidence bundle directory ready for reproducibility-grade evidence capture: SOURCE.md (operator + cluster + git SHA + UTC timestamp), summary.md (verdict skeleton), commands/ (for the four-file .cmd/.stdout/.stderr/.exit tuple capture per shell…

2026년 6월 14일
inference-capacity-sizing
소프트웨어 개발자

SLA-first GPU capacity sizing for a serving deployment: given a tokens-per-minute (TPM) target AND the interactivity SLA (output tokens/s/user), compute the pods and GPUs needed from a model's measured tok/s/user-vs-concurrency curve. Sizing MUST start from…

2026년 6월 14일
inference-decode-step-budget
소프트웨어 개발자

Measure the low-concurrency (c=1..c=8) decode hot-path of a live vLLM pod FAST and CORRECTLY: where each token's time actually goes (GPU-busy vs host-idle gap vs comm), whether the workload is kernel-bound / host-bound / comm-bound, and what the addressable…

2026년 6월 14일
inference-kernel-ncu-profile
소프트웨어 개발자

Capture per-kernel CUDA hardware-counter data (occupancy, achieved warps active, regs/thread, smem/block, DRAM throughput, arithmetic intensity, branch divergence %, warp-stall reason %) from a live vLLM inference pod via an `ncu` debug sidecar (no production…

2026년 6월 14일
inference-kernel-profile
소프트웨어 개발자

Capture per-kernel CUDA profile data from a live vLLM inference pod via an nsys debug sidecar (no production image rebuild). Outputs `.nsys-rep` + summary CSV + top-kernels table that joins with the zymtrace per-kernel breakdown and the inference-perf-bench…

2026년 6월 14일
inference-model-optimize
소프트웨어 개발자

End-to-end orchestrator that takes a NEW model from a bare HuggingFace id to a perf-lake-published, validated CROSS-ENGINE (vLLM + SGLang) champion on B200/GB300. Scaffolds a per-model harness + evidence bundle (run-id == experiment-id), then drives…

2026년 6월 14일
inference-perf-baseline-bridge
소프트웨어 개발자

Bridge between the inference-perf-bench / ai-bench output bundle and the profile-and-optimize perf-baseline registry. Knows the canonical inference perf metric shape (TTFT p50/p95/p99, ITL p50, throughput, tok/s/user, request latency p50, prefix cache hit…

2026년 6월 14일
inference-perf-bench
소프트웨어 개발자

Canonical inference perf-bench skill (formal name. The colloquial alias is `ai-bench` - identical behaviour). Drives NVIDIA AIPerf + the replay-playback dataset against an in-cluster vLLM endpoint to measure TTFT, ITL, throughput, tok/s/user, request latency,…

2026년 6월 14일
수집된 skill 16개 중 8개를 표시합니다.
저장소 5개 중 5개 표시
모든 저장소를 표시했습니다