aboutsummaryrefslogtreecommitdiff
path: root/pplx_server.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* gitignore: track new binary and library namesOnur Gündüz2026-06-141-2431/+0
|
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-141-2/+2
|
* cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz2026-06-141-13/+10
|
* server: fix unused-rc warning in plain BLAS buildsOnur Gündüz2026-06-141-1/+2
|
* cuda: add server contextual pathOnur Gündüz2026-06-141-1/+74
|
* chore: address static analyzer warningsOnur Gündüz2026-06-141-6/+28
|
* server: expose worker stage timingOnur Gündüz2026-06-141-13/+95
|
* tokenizer: add reusable encode workspaceOnur Gündüz2026-06-141-1/+10
|
* server: support http keep-aliveOnur Gündüz2026-06-141-11/+98
|
* mlx: add opt-in 8-bit weight quantizationOnur Gündüz2026-06-141-1/+15
|
* server: bound mlx batches by padded token rowsOnur Gündüz2026-06-141-2/+25
|
* server: reject unsafe mlx model overcommitOnur Gündüz2026-06-141-0/+103
|
* server: simplify context separator logicOnur Gündüz2026-06-141-13/+4
|
* server: batch contextual document inferenceOnur Gündüz2026-06-141-179/+354
|
* server: batch standard requests by token budgetOnur Gündüz2026-06-141-11/+64
|
* server: align embedding quantization with perplexityOnur Gündüz2026-06-141-13/+11
|
* server: support float embedding responsesOnur Gündüz2026-06-141-18/+52
|
* server: add embeddings micro-batchingOnur Gündüz2026-06-141-98/+343
|
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-141-0/+1524