aboutsummaryrefslogtreecommitdiff
Commit message (Expand)AuthorAgeFilesLines
...
* chore: rename sources; binaries pplx-embed, pplx-embed-serverOnur Gündüz2026-06-1412-54/+386
* gitignore: track new binary and library namesOnur Gündüz2026-06-1414-341/+4
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-1419-57/+57
* tests: move kernel goldens into tests/, add make testOnur Gündüz2026-06-141-0/+337
* cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz2026-06-146-230/+441
* build: produce libpplxembed.a and a shared-library targetOnur Gündüz2026-06-141-5/+38
* cuda: store BF16 activations directly in norm and SiLU kernelsOnur Gündüz2026-06-141-51/+114
* build: allow FP reassociation/contraction, keep finite-math offOnur Gündüz2026-06-141-3/+7
* server: fix unused-rc warning in plain BLAS buildsOnur Gündüz2026-06-141-1/+2
* build: add .clang-tidy configurationOnur Gündüz2026-06-141-0/+13
* gitignore: add .vscode directory to ignore listOnur Gündüz2026-06-141-0/+1
* gitignore: add private directory to ignore listOnur Gündüz2026-06-141-0/+1
* mlx: mixed-precision BF16 inference (F32 residual, BF16 weights)Onur Gündüz2026-06-141-7/+71
* cuda: add optional BF16 CUDA weight storage (--cuda-weights bf16)Onur Gündüz2026-06-143-68/+162
* 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 Gündüz2026-06-143-17/+102
* 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 Gündüz2026-06-145-21/+239
* 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 Gündüz2026-06-146-68/+911
* kernels: fix OpenBLAS thread contention and numerical instabilityOnur Gündüz2026-06-142-3/+33
* mlx: split ragged contextual batchesOnur Gündüz2026-06-141-3/+137
* mlx: tune ragged grouping for 4BOnur Gündüz2026-06-141-5/+34
* mlx: prepare contiguous linear weightsOnur Gündüz2026-06-141-4/+21
* mlx: optimize ragged embedding batchesOnur Gündüz2026-06-141-2/+114
* build: add address/undefined sanitizers to debug buildsOnur Gündüz2026-06-141-2/+4
* chore: address static analyzer warningsOnur Gündüz2026-06-145-27/+92
* kernels: parallelize large rmsnorm rowsOnur Gündüz2026-06-141-5/+48
* mlx: use prefix pooling for f32 contextual spansOnur Gündüz2026-06-141-32/+138
* mlx: cache transposed linear weightsOnur Gündüz2026-06-141-4/+46
* server: expose worker stage timingOnur Gündüz2026-06-141-13/+95
* tokenizer: add reusable encode workspaceOnur Gündüz2026-06-144-2/+478
* mlx: keep late maxsim device residentOnur Gündüz2026-06-142-25/+405
* late: add packed maxsim scoringOnur Gündüz2026-06-144-7/+45
* late: add mlx token vector supportOnur Gündüz2026-06-142-8/+235
* late: add CPU token vectors and maxsimOnur Gündüz2026-06-142-5/+223
* all: add validation for late-interaction model compatOnur Gündüz2026-06-142-1/+48
* kernels: vectorize bf16 widening on armOnur Gündüz2026-06-141-0/+14
* kernels: use sgemv for single-row f32 linearOnur Gündüz2026-06-142-4/+11
* kernels: add neon rope apply pathOnur Gündüz2026-06-141-0/+21
* build: add tmp to .gitignoreOnur Gündüz2026-06-141-0/+1