https://researchdev.colfax-intl.com/custom-cuda-and-python/ 2024-04-24T19:35:52+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-CUDA-and-Python.png https://researchdev.colfax-intl.com/introduction-to-transformers/ 2024-04-24T19:36:07+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/attention_figure.png https://researchdev.colfax-intl.com/analog-ai/ 2024-04-24T19:36:17+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-Analog-AI.png https://researchdev.colfax-intl.com/narrow-bit-width-formats-for-deep-learning/ 2024-04-24T19:36:26+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-Narrow-bit-width-formats-e1709687339268.png https://researchdev.colfax-intl.com/proxmox-ve/ 2024-04-24T19:36:35+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-Proxmox-VE.png https://researchdev.colfax-intl.com/software-pipelining-in-the-nvidia-h100-architecture/ 2024-04-24T19:36:43+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-Software-Pipelining-in-H100.png https://researchdev.colfax-intl.com/json-web-token-standard-jwt/ 2024-04-24T19:36:51+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-JSON-Web-Token.png https://researchdev.colfax-intl.com/spec-benchmarks/ 2024-04-24T19:37:00+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-SPEC-Benchmarks.png https://researchdev.colfax-intl.com/a-note-on-the-algebra-of-cute-layouts/ 2024-08-09T22:40:04+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2023/12/algebra-cute-layouts.png https://researchdev.colfax-intl.com/nvidia-hopper-flashattention-2/ 2024-08-09T22:40:09+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2023/12/cuda-kernel-fusion.png https://researchdev.colfax-intl.com/nvidia-hopper-gemm-cutlass/ 2024-08-09T22:40:22+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2023/10/cuda-gemm-cutlass.png https://researchdev.colfax-intl.com/gpu-mode-cutlass-and-flashattention-3/ 2024-11-18T19:26:09+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/11/kernel_pseudocode.png https://researchdev.colfax-intl.com/gpu-passthrough-on-proxmox-ve-8/ 2024-11-18T19:42:33+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/pcie-passthrough-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/pcie-passthrough-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-3.02.51%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-3.07.01%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-3.11.34%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-3.16.12%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-3.26.15%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-6.37.15%E2%80%AFPM-edited.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-6.32.35%E2%80%AFPM-edited.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-6.53.53%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-7.00.02%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-08-at-7.16.46%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-02-at-3.25.45%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-02-at-3.26.38%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/Screenshot-2024-10-02-at-3.31.14%E2%80%AFPM.png https://researchdev.colfax-intl.com/cutlass-tutorial-design-of-a-gemm-kernel/ 2024-11-19T17:21:32+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/09/software-pipeline-scaled.webp https://researchdev.colfax-intl.com/wp-content/uploads/2024/08/Pipeline-illustration.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/08/Pipeline-2-stages-1.png https://researchdev.colfax-intl.com/sharing-nvidia-gpus-at-the-system-level-time-sliced-and-mig-backed-vgpus/ 2024-11-19T17:22:35+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-27.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-27.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-28.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-29.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-22.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-3.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-4.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-5.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-6.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-7.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-8.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-13.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-14.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-15.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-16.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-4.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-5.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-17.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-18.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-19.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-20.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/Screenshot-2024-05-28-at-4.08.52%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-21.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/Screenshot-2024-05-28-at-4.16.00%E2%80%AFPM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-23.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-24.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-26.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-39.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-36.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-33.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-38.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/image-37.png https://researchdev.colfax-intl.com/ubuntu-22-04-netboot-on-servers-with-the-nvidia-grace-hopper-superchip/ 2024-11-19T17:23:06+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/IMG_20240418_130504_HDR-4.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/IMG_20240418_122233_HDR-scaled.jpg https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-4.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-5.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-6.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-7.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-9.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-12.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-11.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-13.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/image-14.png https://researchdev.colfax-intl.com/tutorial-python-binding-for-cuda-libraries-in-pytorch/ 2024-11-19T17:23:25+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/03/Colfax-Research_Landscape_135.png https://researchdev.colfax-intl.com/flashattention-3-fast-and-accurate-attention-with-asynchrony-and-low-precision/ 2024-11-19T17:23:46+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/fp16_benchmark_h256_fp16.jpg https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/flashattention.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/a100_vs_h100.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/tma.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/pingpong.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/2pipeline.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/error_comparison.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/fp16_benchmark-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/fp16_backward.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/fp8_benchmark.png https://researchdev.colfax-intl.com/adding-fp8-to-flashattention/ 2024-11-19T17:24:12+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/figure-3-data-movement.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/fig-1-fp32-wgmma.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/fig-2-fp8-wgmma.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/figure-3-data-movement.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/flops-benchmarks-h100-sxm5.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/params.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/02/rmse.png https://researchdev.colfax-intl.com/deepseek-r1-and-fp8-mixed-precision-training/ 2025-01-28T06:55:47+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/01/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/01/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/01/filled.png https://researchdev.colfax-intl.com/cutlass-tutorial-wgmma-hopper/ 2025-02-07T23:25:46+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/wgmma-64N16-D-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/07/wgmma-64N16-D-1.png https://researchdev.colfax-intl.com/tutorial-matrix-transpose-in-cutlass/ 2025-04-30T17:04:56+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/transpose-chart-5-7-24-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/Screenshot-2024-04-22-at-6.51.01-PM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/Screenshot-2024-04-22-at-6.54.20-PM.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/05/Swizzle-32x32-1-scaled.jpg https://researchdev.colfax-intl.com/wp-content/uploads/2024/04/Screenshot-2024-04-22-at-6.56.35-PM.png https://researchdev.colfax-intl.com/cutlass-tutorial-persistent-kernels-and-stream-k/ 2025-05-17T03:04:48+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/hybrid.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/quantization.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/m1024-wave-quantization-time-tflops.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/split-mn.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/split-mn-more-tiles.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/split-k.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/stream-k.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/dp-reuse.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/hybrid.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/m1024-no-heuristic.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/m1024-w-heuristic.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/rasterization-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/swizzle-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/12/swizzle-3.png https://researchdev.colfax-intl.com/epilogue_visitor_tree/ 2025-06-27T17:40:36+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-14.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-9.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-11.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-7.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-15.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2024/10/image-14.png https://researchdev.colfax-intl.com/cutlass-3-x-apis-orthogonal-reusable-and-composable-abstractions-for-gemm-kernel-design-external/ 2025-07-20T03:59:28+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/07/CUTLASS-GEMM-hierarchy-png.webp https://researchdev.colfax-intl.com/tutorial-hopper-tma/ 2025-11-12T03:29:55+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/06/tma_graphic.png https://researchdev.colfax-intl.com/cutlass-tutorial-sub-byte-gemm-on-nvidia-blackwell-gpus/ 2025-11-15T05:10:16+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tensor-dimension-size-format-sub-bytes-padding-align-b4-16-p64.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tcgen05-packing-formats-mxf8f6f4-smem-dig1.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tcgen05-packing-formats-mxf8f6f4-smem-dig2.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tensor-dimension-size-format-sub-bytes-padding-align-b4-16-p64.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tensor-dimension-size-format-sub-bytes-padding-align-b6-16-p32.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tcgen05-packing-formats-mxf8f6f4-tmem-dig1.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tcgen05-packing-formats-mxf8f6f4-tmem-dig2.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/06/tcgen05-packing-formats-mxf8f6f4-tmem-dig3.png https://researchdev.colfax-intl.com/cutlass-tutorial-writing-gemm-kernels-using-tensor-memory-for-nvidia-blackwell-gpus/ 2025-11-15T05:10:30+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/04/tensor-memory-layout.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/04/tensor-memory-layout.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/04/tcgen05-mma-fragment-3232b.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/04/tcgen05-data-path-layout-d1.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/04/tcgen05-data-path-layout-d2.png https://researchdev.colfax-intl.com/cutlass-tutorial-gemm-with-thread-block-clusters-on-nvidia-blackwell-gpus/ 2025-11-15T05:10:43+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image-3-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image-1-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image-4-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/05/image-5-scaled.png https://researchdev.colfax-intl.com/a-users-guide-to-flexattention-in-flash-attention-cute-dsl/ 2026-02-02T17:38:43+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/11/prefix_lm_mask1.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/11/causal_mask1-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/11/document_mask1.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/11/prefix_lm_mask1.png https://researchdev.colfax-intl.com/flashattention-4-algorithm-and-kernel-pipelining-co-design-for-asymmetric-hardware-scaling/ 2026-03-10T17:44:08+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/FA4_FWD_p3-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/h100_vs_b200_speeds.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/2cta_mma-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/FA4_FWD_p3-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/fa_bwd_p8-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/2cta_fig_2-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/2cta_figure-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/fa4_fwd_causalFalse_hdim128_updated-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/fa4_fwd_causalTrue_hdim128_updated-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/output-10.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/fa4_bwd_causalFalse_hdim128_updated-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/fa4_bwd_causalTrue_hdim128_updated-scaled.png https://researchdev.colfax-intl.com/flashattention-3-for-inference-int8-quantization-and-query-head-packing-for-mqa-gqa-external/ 2026-03-11T02:56:41+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2024/11/packed_qtile.png https://researchdev.colfax-intl.com/flexattention-flashattention-4-fast-and-flexible-external/ 2026-03-11T05:42:22+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/flex_vs_flash.png https://researchdev.colfax-intl.com/cutlass-tutorial-hardware-supported-block-scaling-with-nvidia-blackwell-gpus/ 2026-03-17T17:27:34+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/02/image-4.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/02/image-5.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/02/image-11.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/02/image-12.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/02/image-10.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/image-3.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/02/image-6.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/03/image-2.png https://researchdev.colfax-intl.com/categorical-foundations-for-cute-layouts/ 2026-04-20T18:11:52+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/02-anatopy-of-tuple-mor-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/01-examples-of-tuple-mors.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/02-anatopy-of-tuple-mor-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/03-tuple-mors-with-same-layout-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/04-coalesce-of-tuple-mor.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/05-complement-of-tuple-mor.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/06-composable-tuple-mors.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/07-composition-of-tuple-mors-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/nested_tuple_morphism_1-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/nested_tuple_morphism_2-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/10-tuple-mors-to-compose.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/mutual_refinement.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/pullback_f_to_f.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/13-pushforward-of-g-to-g-prime-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/nested_composition-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2025/09/15-ref-span-tuple-mor-example.png https://researchdev.colfax-intl.com/gpu-mode-fundamentals-of-cute-layout-algebra-and-category-theoretic-interpretation/ 2026-04-20T18:38:25+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/04/logical_division.png https://researchdev.colfax-intl.com/dynamic-persistent-tile-scheduling-with-cluster-launch-control-clc-on-nvidia-blackwell-gpus/ 2026-05-11T15:59:47+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-29.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-30.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-21.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-27.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-22.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-29.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-23.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-24.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-25.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-28.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-26.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-31.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-32.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-33.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/05/image-34.png https://researchdev.colfax-intl.com/cutlass-tutorial-nvfp4-blockscaled-gemm-on-nvidia-rtx-pro-blackwell-gpus-sm12x/ 2026-06-21T15:52:32+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/blockscaled_matmul6-1.gif https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/blockscaled_matmul6-1.gif https://researchdev.colfax-intl.com/wp-content/uploads/2026/06/image-1.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/06/image.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/sf_distribution_v3.gif https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/image-6.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/image-5.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/fp4_gemm_pipelining_v3.gif https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/image-7.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/10/image-11.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/06/image-5.png https://researchdev.colfax-intl.com/optimizing-an-nvfp4-blockscaled-gemm-on-rtx-pro-6000-blackwell-gpu-sm120/ 2026-08-10T01:17:05+00:00 https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v7_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v1_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-2.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-4.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-5.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v2_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-7.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-8.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v3_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-13.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v4_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-15.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-17.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-18.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-20.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v5_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-21.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v6_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-23.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/v7_vs_cublas_bar_bigfont-scaled.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-27.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-28.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-29.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-30.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/image-31.png https://researchdev.colfax-intl.com/wp-content/uploads/2026/08/clc_vs_cublas_bar_bigfont-1-scaled.png