aboutsummaryrefslogtreecommitdiff
path: root/libffwd/mlx.h (unfollow)
Commit message (Expand)AuthorFilesLines
2026-06-27chore: clean up comment formatting and wordingOnur Gündüz1-17/+17
2026-06-25chore: run clang-formatOnur Gündüz1-33/+32
2026-06-21all: split Makefile and reorg library/toolsOnur Gündüz1-61/+56
2026-06-16chore: move sources to src/ with proper names, drop qwen_ prefixOnur Gündüz1-0/+0
2026-06-15late: restore MLX device select/concat used by interaction checkOnur Gündüz1-0/+10
2026-06-15late: batch MLX rerank candidate encoding in one padded passOnur Gündüz1-7/+15
2026-06-15chore: run clang-formatOnur Gündüz1-28/+41
2026-06-14all: add support for Qwen3-Embedding + causal GQA attentionOnur Gündüz1-1/+1
2026-06-14chore: rename projectOnur Gündüz1-44/+44
2026-06-14chore: comments housekeepingOnur Gündüz1-1/+1
2026-06-14dist: remove distributed layer-sharding (protocol, CLI flags, slice APIs)Onur Gündüz1-24/+0
2026-06-14build: export only the public API from the shared libraryOnur Gündüz1-26/+37
2026-06-14chore: rename sources; binaries pplx-embed, pplx-embed-serverOnur Gündüz1-3/+3
2026-06-14gitignore: track new binary and library namesOnur Gündüz1-0/+0
2026-06-14mlx: keep late maxsim device residentOnur Gündüz1-0/+27
2026-06-14late: add mlx token vector supportOnur Gündüz1-0/+24
2026-06-14mlx: add opt-in 8-bit weight quantizationOnur Gündüz1-0/+10
2026-06-14server: batch contextual document inferenceOnur Gündüz1-0/+8
2026-06-14dist: load distributed layer shards selectivelyOnur Gündüz1-0/+8
2026-06-14dist: add distributed layer-slice foundationOnur Gündüz1-0/+13
2026-06-14server: implement HTTP API with libae integrationOnur Gündüz1-0/+8
2026-06-14all: support batched embedding attentionOnur Gündüz1-0/+17
2026-03-28Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz1-8/+7
2026-03-28InitOnur Gündüz1-0/+35