aboutsummaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
* server: resolve contextual separator from vocab, test contextual pathOnur Gündüz2026-06-145-11/+154
|
* tests: drive the HTTP request path in-process in test_serverOnur Gündüz2026-06-144-103/+548
|
* tokenizer: ASCII class table for pretokenizer codepoint checksOnur Gündüz2026-06-142-9/+51
|
* build: add make coverage (clang source-based, llvm-cov)Onur Gündüz2026-06-142-16/+75
|
* build: rename make targets blas->cpu, mlx->metal, shared->libOnur Gündüz2026-06-143-26/+26
|
* server: default micro-batch cap to 32; add scheduler sweep driverOnur Gündüz2026-06-141-3/+6
|
* server: do not idle-reap clients with requests in flightOnur Gündüz2026-06-141-1/+4
|
* late: batch MaxSim as grouped GEMM plus row-max reductionOnur Gündüz2026-06-141-2/+60
|
* cpu: move BF16 widening scratch into the workspaceOnur Gündüz2026-06-144-152/+61
|
* tests: hermetic BPE tokenizer test with fast/slow path equalityOnur Gündüz2026-06-143-0/+191
|
* tokenizer: integer-pair BPE merging with linked-list symbolsOnur Gündüz2026-06-142-5/+241
|
* tests: add server encoder unit tests via EMBED_SERVER_TEST includeOnur Gündüz2026-06-143-1/+97
|
* cuda: follow model file dtype for weight storage by defaultOnur Gündüz2026-06-141-1/+15
|
* tests: make safetensors and bf16-model tests hermetic, join make testOnur Gündüz2026-06-145-25/+273
|
* gitignore: bench binaryOnur Gündüz2026-06-141-0/+1
|
* tests,bench: move generated C checkers into standing filesOnur Gündüz2026-06-145-1/+448
|
* cli: update help textOnur Gündüz2026-06-141-2/+0
|
* 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
|