aboutsummaryrefslogtreecommitdiff
path: root/main.c (follow)
Commit message (Expand)AuthorAgeFilesLines
* gitignore: track new binary and library namesOnur Gündüz2026-06-141-825/+0
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-141-2/+2
* cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz2026-06-141-203/+42
* cuda: add optional BF16 CUDA weight storage (--cuda-weights bf16)Onur Gündüz2026-06-141-0/+30
* cuda: add fast GEMM mode (--cuda-fast-gemm mode)Onur Gündüz2026-06-141-0/+25
* cuda: add server contextual pathOnur Gündüz2026-06-141-6/+2
* cuda: add initial CUDA embedding backendOnur Gündüz2026-06-141-9/+71
* chore: address static analyzer warningsOnur Gündüz2026-06-141-4/+5
* tokenizer: add reusable encode workspaceOnur Gündüz2026-06-141-1/+18
* dist: add fp16 activation transportOnur Gündüz2026-06-141-0/+21
* mlx: add opt-in 8-bit weight quantizationOnur Gündüz2026-06-141-7/+53
* server: reject unsafe mlx model overcommitOnur Gündüz2026-06-141-0/+7
* server: batch standard requests by token budgetOnur Gündüz2026-06-141-0/+12
* dist: add direct two-node fp32 inferenceOnur Gündüz2026-06-141-18/+123
* server: add embeddings micro-batchingOnur Gündüz2026-06-141-2/+14
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-141-22/+161
* server: report workspace memoryOnur Gündüz2026-06-141-3/+11
* api: simplify embedding APIOnur Gündüz2026-06-141-7/+25
* api: split model and workspace ownershipOnur Gündüz2026-06-141-1/+1
* all: support batched embedding attentionOnur Gündüz2026-06-141-70/+213
* Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz2026-03-281-249/+230
* InitOnur Gündüz2026-03-281-0/+363