v2.5

What's Changed

• [HGEMM] Update HGEMM README.md by @DefTruth in #120
• [HGEMM] Add plot tflops function by @DefTruth in #121
• [HGEMM] Add NVIDIA RTX 3090 Laptop perf plot by @DefTruth in #122
• [PERF] Update HGEMM benchmark scripts by @DefTruth in #123
• [HGEMM] Add HGEMM L20/4090 benchmark figures by @DefTruth in #124
• Bump up to v2.5 by @DefTruth in #125

Full Changelog: v2.4.18...v2.5

v2.4.18

What's Changed

• Update README.md by @DefTruth in #115
• [HGEMM] Update HGEMM Supported Matrix by @DefTruth in #116
• [HGEMM] Update HGEMM/SGEMM Supported Matrix by @DefTruth in #117
• [README] Update HGEMM/SGEMM Supported Matrix by @DefTruth in #118
• [HGEMM] Add NVIDIA RTX 4090 benchmark by @DefTruth in #119

Full Changelog: v2.4.17...v2.4.18

v2.4.17

What's Changed

• [NMS] Add nms f32 cuda kernel. by @bear-zd in #102
• [HGEMM] Add some note to collective store by @DefTruth in #103
• [HGEMM] Add HGEMM MMA Col Major Kernel by @DefTruth in #104
• [HGEMM] Update HGEMM benchmark scripts by @DefTruth in #105
• [HGEMM] Add Warp Swizzle as template param by @DefTruth in #106
• [HGEMM] add -Xptxas -v compile flag by @DefTruth in #107
• [HGEMM] Try reduce registers usage by @DefTruth in #108
• [HGEMM] Update HGEMM MMA/WMMA Usage by @DefTruth in #109
• [HGEMM][Docs] Add HGEMM Supported Matrix by @DefTruth in #110
• [HGEMM] Add M=N=K option for benchmark by @DefTruth in #111
• [HGEMM] Update HGEMM/SGEMM Supported Matrix by @DefTruth in #112
• [README] Update HGEMM/SGEMM Supported matrix by @DefTruth in #113
• [Docs] Update HGEMM/SGEMM Supported Matrix by @DefTruth in #114

Full Changelog: v2.4.16...v2.4.17

HGEMM Warp Swizzle/Reg Buffers

What's Changed

• [HGEMM] HGEMM MMA with Reg Double Buffers by @DefTruth in #99
• [HGEMM] ldmatrix.x4.trans with reg double buffers by @DefTruth in #100
• [HGEMM] collective store via warp shfl&reg reuse by @DefTruth in #101

Full Changelog: v2.4.15...v2.4.16

HGEMM Up to 115 TFLOPS:L20

What's Changed

• [HGEMM] Add MMA 16816 swizzle, Up to 115 TFLOPS by @DefTruth in #98

Full Changelog: v2.4.13...v2.4.15

HGEMM Up to 113 TFLOPS:L20

What's Changed

• [Mat][Trans] Add f32/f32x4 row/col first kernel by @bear-zd in #89
• [Docs][Contribute] Add How to contribute Notes by @DefTruth in #90
• [HGEMM] optimize SMEM padding, up to 113 TFLOPS by @DefTruth in #92
• [Mat][Trans] Add f32x4_shared/bcf row/col first kernel. by @bear-zd in #91
• [Docs] rename mat_transpose -> mat-transpose by @DefTruth in #93
• [HGEMM] Add GeForce RTX 3080 Laptop benchmark by @DefTruth in #94
• [HGEMM] update HGEMM benchmark option by @DefTruth in #95
• [HGEMM] Refactor HGEMM WMMA 161616 kernels by @DefTruth in #96
• [HGEMM] Update HGEMM WMMA Benchmark by @DefTruth in #97

Full Changelog: v2.4.12...v2.4.13

v2.4.12 SGEMM TF32 Swizzle

What's Changed

• [SGEMM] SGEMM TF32 Thread Block Swizzle by @DefTruth in #84
• [HGEMM] mma4x4_warp4x4_stages with swizzle by @DefTruth in #86
• [SWISH] support Swish F32/F16 kernel by @wangzijian1010 in #85
• [SGEMM] Update SGEMM TF32 Benchmark by @DefTruth in #87

New Contributors

• @wangzijian1010 made their first contribution in #85

Full Changelog: v2.4.11...v2.4.12

v2.4.11 HGEMM Block Swizzle

What's Changed

• [Docs] Update README.md by @DefTruth in #81
• [HEGMM] HGEMM WMMA Thread Block Swizzle by @DefTruth in #82
• [HGEMM] make thread block swizzle stride as N/4 by @DefTruth in #83

Full Changelog: v2.4.10...v2.4.11

v2.4.10 SGEMM TF32 Stage 2/3

What's Changed

• [HGEMM] HGEMM WMMA Stage mma4x2+warp4x4 by @DefTruth in #76
• [SGEMM] Add SGEMM WMMA TF32 Stage2/3 by @DefTruth in #77
• [SGEMM] Add cuBLAS SGEMM F32/TF32 baseline by @DefTruth in #78
• [SGEMM] Add Kernel cudaFuncSetAttribute hint by @DefTruth in #79
• [RoPE] Add minimal RoPE f32/f32x4 pack impl by @bear-zd in #80

Full Changelog: v2.4.9...v2.4.10

v2.4.9 HGEMM WMMA Stage

What's Changed

• [HGEMM] Add HGEMM WMMA Double Buffers by @DefTruth in #69
• [Embedding] Add embedding kernel f32/x4/x4_pack, f16/x8/x8_pack by @bear-zd in #68
• [HGEMM] Add HGEMM mma4x2, warp2x4x2 kernel by @DefTruth in #70
• [HGEMM] HGEMM WMMA with Reg double buffers by @DefTruth in #71
• [HGEMM] Add HGEMM WMMA Stage 3/4 Kernel by @DefTruth in #74
• [Softmax] Add online softmax f32x4 pack kernel by @bear-zd in #73
• [HEGMM][Bugfix] fix HGEMM Stage cp.async error by @DefTruth in #75

Full Changelog: v2.4.8...v2.4.9