v2.3.1 f16x8 Pack Elementwise

What's Changed

• [FA2][Half] Add FA2 f16_mma_m16n8k16 kernel by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/35
• [Refactor][7/N] CUDA Learn Notes refactor Part-7 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/36
• Clamped input range in Sigmoid kernel to prevent overflow by @Phoenix8215 in https://github.com/DefTruth/CUDA-Learn-Notes/pull/37
• [Sigmoid][F16] Add f16x8_pack kernel, boost 1.5x ~ by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/39
• [Elementwise][Half] support f16x8_pack kernel, boost 1.1x by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/40
• [FlashAttention] replace FLOAT4 with LDST128BITS macro by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/41
• [RELU][FP16] Add f16x8_pack kernel, boost 2.1x by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/42

New Contributors

• @Phoenix8215 made their first contribution in https://github.com/DefTruth/CUDA-Learn-Notes/pull/37

Full Changelog: DefTruth/CUDA-Learn-Notes@v2.3...v2.3.1

v2.3 Refactor 6/N

What's Changed

• [Refactor][6/N] CUDA Learn Notes refactor Part-6 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/17
• [Refactor][5/N] CUDA Learn Notes refactor Part-6 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/18
• [LayerNorm][Half] support fp16x8 packed LayerNorm by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/19
• [Reduce][Half] add HALF2 & BFLOAT2 macro by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/21
• [RMSNorm][Half] support fp16x8 packed RMSNorm by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/22
• [Bugfix][Kernel] fixed some kernel blocks calculate errors by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/23
• [Elementwise][Half] support fp16x8 packed Elementwise by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/24
• [Elementwise][Half] support fp16x8 packed Elementwise by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/25
• [RELU][Half] support fp16x8 RELU kernel by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/26
• [RMSNorm] support f16x8_f32 RMSNorm by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/28
• [RMSNorm][Kernel] Add FLOAT2/HALF2_VARIANCE macro by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/29
• [LayerNorm][Kernel] Add HALF2 SUM/SUB/VAR macro by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/30
• [HGEMM] Add slicked_k&t_8x8_sliced_k_f16x4 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/31
• [HGEMV][Half] support hgemv k32/k128/f16 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/32
• [FlashAttention] Refactor flash_attn_1_fwd_f32 kernel by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/33
• Bump up to v2.3 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/34

Full Changelog: DefTruth/CUDA-Learn-Notes@v2.2...v2.3

v2.2 Refactor 5/N

What's Changed

• [Refactor][5/N] CUDA Learn Notes refactor Part-5 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/15
• Bump up to v2.2 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/16

Full Changelog: DefTruth/CUDA-Learn-Notes@2.1...v2.2

v2.1 Refactor 4/N Part-4

What's Changed

• [Refactor][4/N] CUDA Learn Notes refactor Part-4 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/10
• [Refactor][4/N] CUDA Learn Notes refactor Part-4 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/11
• [Refactor][4/N] CUDA Learn Notes refactor Part-4 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/12
• [Refactor][4/N] CUDA Learn Notes refactor Part-4 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/13
• [Refactor][4/N] CUDA Learn Notes refactor Part-4 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/14

Full Changelog: DefTruth/CUDA-Learn-Notes@v2.0...2.1

v2.0 Refactor 4/N

Full Changelog: DefTruth/CUDA-Learn-Notes@v0.8...v2.0

v0.8

What's Changed

• Bump up to v0.8 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/9

Full Changelog: DefTruth/CUDA-Learn-Notes@v0.7...v0.8

CUDA Learn Note v0.7

Full Changelog: DefTruth/CUDA-Learn-Notes@v0.5...v0.6

What's Changed

• Bump up to v0.7 by @DefTruth in https://github.com/DefTruth/CUDA-Learn-Notes/pull/8

New Contributors

• @DefTruth made their first contribution in https://github.com/DefTruth/CUDA-Learn-Notes/pull/8

Full Changelog: DefTruth/CUDA-Learn-Notes@v0.6...v0.7

CUDA Learn Notes v0.5

Full Changelog: DefTruth/CUDA-Learn-Notes@v0.3...v0.5

v0.3 flash_attn-1 fwd f32

Full Changelog: v0.2...v0.3

CUDA Learn Note v0.2

Full Changelog: v0.1...v0.2