aboutsummaryrefslogtreecommitdiff
Commit message (Expand)AuthorAgeFilesLines
* mlx: tune ragged grouping for 4BOnur Gündüz2026-06-141-5/+34
* mlx: prepare contiguous linear weightsOnur Gündüz2026-06-141-4/+21
* mlx: optimize ragged embedding batchesOnur Gündüz2026-06-141-2/+114
* build: add address/undefined sanitizers to debug buildsOnur Gündüz2026-06-141-2/+4
* chore: address static analyzer warningsOnur Gündüz2026-06-145-27/+92
* kernels: parallelize large rmsnorm rowsOnur Gündüz2026-06-141-5/+48
* mlx: use prefix pooling for f32 contextual spansOnur Gündüz2026-06-141-32/+138
* mlx: cache transposed linear weightsOnur Gündüz2026-06-141-4/+46
* server: expose worker stage timingOnur Gündüz2026-06-141-13/+95
* tokenizer: add reusable encode workspaceOnur Gündüz2026-06-144-2/+478
* mlx: keep late maxsim device residentOnur Gündüz2026-06-142-25/+405
* late: add packed maxsim scoringOnur Gündüz2026-06-144-7/+45
* late: add mlx token vector supportOnur Gündüz2026-06-142-8/+235
* late: add CPU token vectors and maxsimOnur Gündüz2026-06-142-5/+223
* all: add validation for late-interaction model compatOnur Gündüz2026-06-142-1/+48
* kernels: vectorize bf16 widening on armOnur Gündüz2026-06-141-0/+14
* kernels: use sgemv for single-row f32 linearOnur Gündüz2026-06-142-4/+11
* kernels: add neon rope apply pathOnur Gündüz2026-06-141-0/+21
* build: add tmp to .gitignoreOnur Gündüz2026-06-141-0/+1
* dist: add fp16 activation transportOnur Gündüz2026-06-143-23/+191
* server: support http keep-aliveOnur Gündüz2026-06-141-11/+98
* mlx: add opt-in 8-bit weight quantizationOnur Gündüz2026-06-147-33/+332
* cpu: reuse tiled attention scratch buffersOnur Gündüz2026-06-143-15/+77
* mlx: harden model and buffer validationOnur Gündüz2026-06-141-46/+156
* server: bound mlx batches by padded token rowsOnur Gündüz2026-06-141-2/+25
* mlx: simplify equal-length embedding poolingOnur Gündüz2026-06-141-24/+35
* mlx: pool contextual bf16 spans before wideningOnur Gündüz2026-06-141-11/+9
* server: reject unsafe mlx model overcommitOnur Gündüz2026-06-145-0/+129
* server: simplify context separator logicOnur Gündüz2026-06-142-13/+5
* server: batch contextual document inferenceOnur Gündüz2026-06-145-226/+567
* mlx: pool contextual spans on deviceOnur Gündüz2026-06-141-17/+95
* cpu: tile packed attention through blasOnur Gündüz2026-06-141-54/+110
* server: batch standard requests by token budgetOnur Gündüz2026-06-143-11/+77
* dist: add direct two-node fp32 inferenceOnur Gündüz2026-06-144-19/+874
* dist: load distributed layer shards selectivelyOnur Gündüz2026-06-144-29/+122
* build: add client directory to .gitignoreOnur Gündüz2026-06-141-0/+1
* dist: add distributed layer-slice foundationOnur Gündüz2026-06-144-228/+412
* api: add opt-in l2 normalization helperOnur Gündüz2026-06-142-3/+40
* server: align embedding quantization with perplexityOnur Gündüz2026-06-144-51/+28
* server: support float embedding responsesOnur Gündüz2026-06-141-18/+52
* server: add embeddings micro-batchingOnur Gündüz2026-06-143-100/+358
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-1422-27/+4715
* build: add plx_server to .gitignoreOnur Gündüz2026-06-141-0/+1
* 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 Gündüz2026-06-143-3/+77
* kernels,cpu: fuse tiny BF16 gate up projectionsOnur Gündüz2026-06-143-3/+126
* kernels,cpu: fuse small BF16 QKV projectionsOnur Gündüz2026-06-143-20/+67
* cpu: reuse MLP scratch bufferOnur Gündüz2026-06-141-6/+3