aboutsummaryrefslogtreecommitdiff
path: root/main.c (unfollow)
Commit message (Expand)AuthorFilesLines
2026-06-14gitignore: track new binary and library namesOnur Gündüz1-825/+0
2026-06-14kernels: drop asr_ prefix namingOnur Gündüz1-2/+2
2026-06-14cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz1-203/+42
2026-06-14cuda: add optional BF16 CUDA weight storage (--cuda-weights bf16)Onur Gündüz1-0/+30
2026-06-14cuda: add fast GEMM mode (--cuda-fast-gemm mode)Onur Gündüz1-0/+25
2026-06-14cuda: add server contextual pathOnur Gündüz1-6/+2
2026-06-14cuda: add initial CUDA embedding backendOnur Gündüz1-9/+71
2026-06-14chore: address static analyzer warningsOnur Gündüz1-4/+5
2026-06-14tokenizer: add reusable encode workspaceOnur Gündüz1-1/+18
2026-06-14dist: add fp16 activation transportOnur Gündüz1-0/+21
2026-06-14mlx: add opt-in 8-bit weight quantizationOnur Gündüz1-7/+53
2026-06-14server: reject unsafe mlx model overcommitOnur Gündüz1-0/+7
2026-06-14server: batch standard requests by token budgetOnur Gündüz1-0/+12
2026-06-14dist: add direct two-node fp32 inferenceOnur Gündüz1-18/+123
2026-06-14server: add embeddings micro-batchingOnur Gündüz1-2/+14
2026-06-14server: implement HTTP API with libae integrationOnur Gündüz1-22/+161
2026-06-14server: report workspace memoryOnur Gündüz1-3/+11
2026-06-14api: simplify embedding APIOnur Gündüz1-7/+25
2026-06-14api: split model and workspace ownershipOnur Gündüz1-1/+1
2026-06-14all: support batched embedding attentionOnur Gündüz1-70/+213
2026-03-28Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz1-249/+230
2026-03-28InitOnur Gündüz1-0/+363