https://app.gpuflight.com/tryhttps://app.gpuflight.com/try/meet-the-profilerhttps://app.gpuflight.com/try/vector-add-occupancyhttps://app.gpuflight.com/try/vector-add-grid-stride-loophttps://app.gpuflight.com/try/vector-add-warp-occupancyhttps://app.gpuflight.com/try/vector-add-shared-memory-occupancyhttps://app.gpuflight.com/try/reduction-global-atomichttps://app.gpuflight.com/try/warp-shuffle-reductionhttps://app.gpuflight.com/try/matmul-tilinghttps://app.gpuflight.com/try/matrix-transpose-coalescinghttps://app.gpuflight.com/try/streams-overlaphttps://app.gpuflight.com/try/saxpy-coalesced-memory-accesshttps://app.gpuflight.com/try/stencil-1d-shared-halohttps://app.gpuflight.com/try/shared-memory-bank-mappinghttps://app.gpuflight.com/try/matrix-transpose-bank-conflictshttps://app.gpuflight.com/try/tensor-core-wmma-activationhttps://app.gpuflight.com/try/tensor-core-fragment-accumulationhttps://app.gpuflight.com/try/read-only-lookup-localityhttps://app.gpuflight.com/try/constant-memory-broadcasthttps://app.gpuflight.com/try/async-tile-prefetchhttps://app.gpuflight.com/try/tma-tile-transferhttps://app.gpuflight.com/try/pytorch-transfer-churnhttps://app.gpuflight.com/try/pytorch-batch-the-workhttps://app.gpuflight.com/try/pytorch-hidden-synchttps://app.gpuflight.com/try/pytorch-stage-the-batchhttps://app.gpuflight.com/try/cub-block-reducehttps://app.gpuflight.com/try/matmul-register-blocking-1dhttps://app.gpuflight.com/try/softmax-row-reductionhttps://app.gpuflight.com/try/softmax-online-single-passhttps://app.gpuflight.com/try/layernorm-row-kernelhttps://app.gpuflight.com/try/layernorm-welford-one-passhttps://app.gpuflight.com/try/rmsnorm-fused-scalehttps://app.gpuflight.com/try/elementwise-fusion-warmuphttps://app.gpuflight.com/try/fused-swigluhttps://app.gpuflight.com/try/gemv-w8-dequanthttps://app.gpuflight.com/try/embedded-lifecyclehttps://app.gpuflight.com/try/inference-batchinghttps://app.gpuflight.com/try/inference-kv-cachehttps://app.gpuflight.com/try/first-contact-cpu-baselinehttps://app.gpuflight.com/try/first-contact-cuda-baselinehttps://app.gpuflight.com/try/first-contact-profile-baselinehttps://app.gpuflight.com/try/first-contact-shared-memoryhttps://app.gpuflight.com/try/first-contact-gemmhttps://app.gpuflight.com/try/vector-add-cpu-baselinehttps://app.gpuflight.com/try/vector-add-cuda-baselinehttps://app.gpuflight.com/try/reduction-cpu-baselinehttps://app.gpuflight.com/try/reduction-atomic-baselinehttps://app.gpuflight.com/try/decoder-block-cpu-referencehttps://app.gpuflight.com/try/decoder-block-cuda-pipelinehttps://app.gpuflight.com/try/decoder-block-packed-qkvhttps://app.gpuflight.com/try/decoder-block-rope-gqahttps://app.gpuflight.com/try/decoder-block-causal-attentionhttps://app.gpuflight.com/try/decoder-block-online-attentionhttps://app.gpuflight.com/try/stencil-2d-halo-tilehttps://app.gpuflight.com/try/stencil-2d-register-rowshttps://app.gpuflight.com/try/stencil-3d-plane-tilehttps://app.gpuflight.com/try/stencil-3d-register-planeshttps://app.gpuflight.com/try/telemetry-collect-slow-eventshttps://app.gpuflight.com/try/telemetry-ordered-compactionhttps://app.gpuflight.com/try/telemetry-latency-histogramhttps://app.gpuflight.com/try/telemetry-filter-in-placehttps://app.gpuflight.com/try/rtx6000-polynomial-challengehttps://app.gpuflight.com/try/pytorch-input-prefetchhttps://app.gpuflight.com/try/pytorch-compile-graph-breakshttps://app.gpuflight.com/try/pytorch-attention-sdpahttps://app.gpuflight.com/try/pytorch-dynamic-shapeshttps://app.gpuflight.com/try/pytorch-serving-latencyhttps://app.gpuflight.com/try/pytorch-materializationhttps://app.gpuflight.com/try/pytorch-cuda-graphshttps://app.gpuflight.com/try/pytorch-inference-memoryhttps://app.gpuflight.com/try/pytorch-training-memory