aboutsummaryrefslogtreecommitdiff
path: root/src/embed.h (unfollow)
Commit message (Expand)AuthorFilesLines
2026-06-21all: split Makefile and reorg library/toolsOnur Gündüz1-357/+0
2026-06-16all: add SentencePiece XLM-R supportOnur Gündüz1-0/+2
2026-06-16chore: move sources to src/ with proper names, drop qwen_ prefixOnur Gündüz1-1/+0
2026-06-16all: support BERT tanh-GeLU (gelu_new / gelu_pytorch_tanh)Onur Gündüz1-0/+9
2026-06-15cpu: add the BERT encoder family forward and loaderOnur Gündüz1-0/+8
2026-06-15all: add CLS first-token poolingOnur Gündüz1-0/+1
2026-06-15all: support GTE-Qwen2 embeddingsOnur Gündüz1-0/+2
2026-06-15late: batch CPU rerank candidate encoding in one packed forwardOnur Gündüz1-0/+19
2026-06-15chore: run clang-formatOnur Gündüz1-41/+67
2026-06-14all: add Qwen3-Embedding-4B + fix terminal tokenOnur Gündüz1-1/+6
2026-06-14all: add support for Qwen3-Embedding + causal GQA attentionOnur Gündüz1-16/+32
2026-06-14chore: rename projectOnur Gündüz1-57/+57
2026-06-14chore: comments housekeepingOnur Gündüz1-4/+2
2026-06-14dist: remove distributed layer-sharding (protocol, CLI flags, slice APIs)Onur Gündüz1-32/+0
2026-06-14build: export only the public API from the shared libraryOnur Gündüz1-30/+41
2026-06-14chore: rename sources; binaries pplx-embed, pplx-embed-serverOnur Gündüz1-1/+1
2026-06-14gitignore: track new binary and library namesOnur Gündüz1-0/+0
2026-06-14late: add packed maxsim scoringOnur Gündüz1-0/+12
2026-06-14late: add CPU token vectors and maxsimOnur Gündüz1-0/+35
2026-06-14server: simplify context separator logicOnur Gündüz1-0/+1
2026-06-14server: batch contextual document inferenceOnur Gündüz1-0/+17
2026-06-14dist: load distributed layer shards selectivelyOnur Gündüz1-0/+12
2026-06-14dist: add distributed layer-slice foundationOnur Gündüz1-0/+31
2026-06-14api: add opt-in l2 normalization helperOnur Gündüz1-0/+9
2026-06-14server: align embedding quantization with perplexityOnur Gündüz1-5/+8
2026-06-14server: implement HTTP API with libae integrationOnur Gündüz1-0/+25
2026-06-14server: report workspace memoryOnur Gündüz1-0/+8
2026-06-14cpu: support BF16 weightsOnur Gündüz1-1/+1
2026-06-14api: simplify embedding APIOnur Gündüz1-90/+12
2026-06-14api: split model and workspace ownershipOnur Gündüz1-5/+47
2026-06-14all: support batched embedding attentionOnur Gündüz1-0/+31
2026-03-28Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz1-94/+53
2026-03-28InitOnur Gündüz1-0/+186