aboutsummaryrefslogtreecommitdiff
path: root/pplx_embed_cuda.cu (follow)
Commit message (Collapse)AuthorAgeFilesLines
* gitignore: track new binary and library namesOnur Gündüz2026-06-141-1204/+0
|
* cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz2026-06-141-2/+2
|
* cuda: store BF16 activations directly in norm and SiLU kernelsOnur Gündüz2026-06-141-51/+114
|
* cuda: add optional BF16 CUDA weight storage (--cuda-weights bf16)Onur Gündüz2026-06-141-68/+131
|
* cuda: unify attention on one path; drop the max_seq>=64 dispatchOnur Gündüz2026-06-141-73/+8
|
* cuda: add fast GEMM mode (--cuda-fast-gemm mode)Onur Gündüz2026-06-141-17/+75
|
* cuda: clarify comment gemm_computeOnur Gündüz2026-06-141-2/+3
|
* cuda: add opt-in BF16 tensor-core GEMM modeOnur Gündüz2026-06-141-21/+34
|
* cuda: replace long-seq attention with cuBLAS GEMM attentionOnur Gündüz2026-06-141-158/+124
|
* cuda: replace tiled attention with warp-per-query reductionOnur Gündüz2026-06-141-98/+105
|
* cuda: extend tiled attention to ragged micro-batchesOnur Gündüz2026-06-141-3/+105
|
* cuda: add tiled single attentionOnur Gündüz2026-06-141-4/+64
|
* cuda: optimize rmsnorm reductionOnur Gündüz2026-06-141-34/+29
|
* cuda: add server contextual pathOnur Gündüz2026-06-141-14/+159
|
* cuda: optimize projection pathOnur Gündüz2026-06-141-87/+118
|
* cuda: fuse qkv projectionOnur Gündüz2026-06-141-44/+78
|
* cuda: accumulate residual projectionsOnur Gündüz2026-06-141-21/+18
|
* cuda: optimize attention baselineOnur Gündüz2026-06-141-44/+47
|
* cuda: add initial CUDA embedding backendOnur Gündüz2026-06-141-0/+731