aboutsummaryrefslogtreecommitdiff
path: root/pplx_embed.c (follow)
Commit message (Expand)AuthorAgeFilesLines
* gitignore: track new binary and library namesOnur Gündüz2026-06-141-1483/+0
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-141-2/+2
* cuda: add initial CUDA embedding backendOnur Gündüz2026-06-141-57/+1
* chore: address static analyzer warningsOnur Gündüz2026-06-141-2/+5
* late: add packed maxsim scoringOnur Gündüz2026-06-141-3/+22
* late: add CPU token vectors and maxsimOnur Gündüz2026-06-141-5/+188
* all: add validation for late-interaction model compatOnur Gündüz2026-06-141-1/+25
* cpu: reuse tiled attention scratch buffersOnur Gündüz2026-06-141-3/+23
* server: batch contextual document inferenceOnur Gündüz2026-06-141-12/+69
* dist: load distributed layer shards selectivelyOnur Gündüz2026-06-141-14/+46
* dist: add distributed layer-slice foundationOnur Gündüz2026-06-141-21/+113
* api: add opt-in l2 normalization helperOnur Gündüz2026-06-141-3/+31
* server: align embedding quantization with perplexityOnur Gündüz2026-06-141-23/+5
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-141-0/+62
* cpu: keep batch offsets in workspaceOnur Gündüz2026-06-141-10/+38
* cpu: tighten workspace growthOnur Gündüz2026-06-141-4/+14
* cpu: reduce initial workspace capacityOnur Gündüz2026-06-141-1/+2
* server: report workspace memoryOnur Gündüz2026-06-141-0/+58
* kernels,cpu: fuse tiny BF16 gate up projectionsOnur Gündüz2026-06-141-3/+26
* kernels,cpu: fuse small BF16 QKV projectionsOnur Gündüz2026-06-141-3/+24
* cpu: reuse MLP scratch bufferOnur Gündüz2026-06-141-6/+3
* cpu: support BF16 weightsOnur Gündüz2026-06-141-46/+142
* cpu: fuse CPU embedding hot pathsOnur Gündüz2026-06-141-11/+23
* cpu: validate model tensor shapesOnur Gündüz2026-06-141-21/+90
* cpu: harden workspace allocationOnur Gündüz2026-06-141-41/+125
* api: simplify embedding APIOnur Gündüz2026-06-141-80/+46
* api: split model and workspace ownershipOnur Gündüz2026-06-141-98/+203
* all: support batched embedding attentionOnur Gündüz2026-06-141-81/+180
* Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz2026-03-281-219/+240
* InitOnur Gündüz2026-03-281-0/+447