aboutsummaryrefslogtreecommitdiff
Commit message (Expand)AuthorAgeFilesLines
...
* 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
* tokenizer: reduce merge allocationOnur Gündüz2026-06-141-10/+41
* safetensors: harden parser limitsOnur Gündüz2026-06-141-23/+99
* kernels: validate real BF16 artifactsOnur Gündüz2026-06-142-6/+77
* cpu: support BF16 weightsOnur Gündüz2026-06-142-47/+143
* cpu: fuse CPU embedding hot pathsOnur Gündüz2026-06-143-11/+51
* tokenizer: refactor encoding pipeline to support pre-tokenizationOnur Gündüz2026-06-141-5/+397
* cpu: validate model tensor shapesOnur Gündüz2026-06-141-21/+90
* kernels: avoid tiny packed attention dispatchOnur Gündüz2026-06-141-1/+7
* cpu: harden workspace allocationOnur Gündüz2026-06-141-41/+125
* api: simplify embedding APIOnur Gündüz2026-06-145-178/+88
* api: split model and workspace ownershipOnur Gündüz2026-06-143-104/+251
* all: support batched embedding attentionOnur Gündüz2026-06-147-210/+689
* Update README.mdv0.1.0Onur Gündüz2026-03-291-35/+103
* Add benchmark scriptOnur Gündüz2026-03-282-0/+546
* Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz2026-03-2811-869/+830
* InitOnur Gündüz2026-03-2816-0/+5109
* Add README.mdOnur Gündüz2026-03-281-0/+1