andodeki/makepad
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
makepad/libs/ai/cuda/kernels
History
Exact
Admin a2aaa8f778 ai-body: the FP8 bias rides a column-broadcast add on the device 
The FP8 backbone mode added each linear's bias by downloading, tiling and
re-uploading it per call, which cost more than the FP8 GEMM saved. A
gpu_add_cols_broadcast op (CUDA kernel; host loop on the Metal tensor
backend) adds a cols-wide bias to every row on the device, and each linear
keeps its bias resident after the first upload.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-02 00:05:03 +02:00
..
llm ai backbone: the hub era — makepad_ai deleted, every backend is a hub pipe; machine residency elections, job leases, ETA placement; the store only stores; creator pipelines run in the app (aicore) 2026-09-01 16:46:31 +02:00
affine.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
diffusion_ops.cu ai-body: the FP8 bias rides a column-broadcast add on the device 2026-09-02 00:05:03 +02:00
gated_delta_net.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
kquants.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
nvfp4.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
nvfp4_mmq.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
ops.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
paint_extras.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
rife.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
roformer.cu ai backbone: the hub era — makepad_ai deleted, every backend is a hub pipe; machine residency elections, job leases, ETA placement; the store only stores; creator pipelines run in the app (aicore) 2026-09-01 16:46:31 +02:00
splat.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00
ssm_conv.cu libs/ai: one AI stack, replacing libs/ggml, llama, mlx, cuda, tts, voice2 and pbr_paint 2026-08-23 01:34:35 +02:00