aboutsummaryrefslogtreecommitdiff
path: root/pplx_embed_mlx.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* gitignore: track new binary and library namesOnur Gündüz2026-06-141-2296/+0
|
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-141-1/+1
|
* mlx: mixed-precision BF16 inference (F32 residual, BF16 weights)Onur Gündüz2026-06-141-7/+71
|
* mlx: split ragged contextual batchesOnur Gündüz2026-06-141-3/+137
|
* 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
|
* chore: address static analyzer warningsOnur Gündüz2026-06-141-5/+13
|
* mlx: use prefix pooling for f32 contextual spansOnur Gündüz2026-06-141-32/+138
|
* mlx: cache transposed linear weightsOnur Gündüz2026-06-141-4/+46
|
* mlx: keep late maxsim device residentOnur Gündüz2026-06-141-25/+378
|
* late: add mlx token vector supportOnur Gündüz2026-06-141-8/+211
|
* all: add validation for late-interaction model compatOnur Gündüz2026-06-141-0/+23
|
* mlx: add opt-in 8-bit weight quantizationOnur Gündüz2026-06-141-21/+206
|
* mlx: harden model and buffer validationOnur Gündüz2026-06-141-46/+156
|
* mlx: simplify equal-length embedding poolingOnur Gündüz2026-06-141-24/+35
|
* mlx: pool contextual bf16 spans before wideningOnur Gündüz2026-06-141-11/+9
|
* server: batch contextual document inferenceOnur Gündüz2026-06-141-35/+119
|
* mlx: pool contextual spans on deviceOnur Gündüz2026-06-141-17/+95
|
* dist: load distributed layer shards selectivelyOnur Gündüz2026-06-141-15/+56
|
* dist: add distributed layer-slice foundationOnur Gündüz2026-06-141-207/+255
|
* server: align embedding quantization with perplexityOnur Gündüz2026-06-141-10/+4
|
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-141-0/+156
|
* kernels: validate real BF16 artifactsOnur Gündüz2026-06-141-6/+25
|
* api: simplify embedding APIOnur Gündüz2026-06-141-1/+1
|
* all: support batched embedding attentionOnur Gündüz2026-06-141-59/+137
|
* Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz2026-03-281-270/+208
| | | | | | | | | | | | - Updated `pplx_embed.h` to support new embedding models: `pplx-embed-v1-4b` and `pplx-embed-context-v1-4b`. - Simplified model configuration structure and constants for better maintainability. - Enhanced comments for clarity on model architecture and configuration. - Modified `pplx_embed_mlx.c` to streamline loading of model weights and configuration from `config.json`. - Improved memory management and error handling in the MLX backend. - Updated embedding computation to support dynamic hidden sizes based on model configuration. - Added `pplx_mlx_config` function to retrieve model configuration details. - Updated README.md - Added .gitignore
* InitOnur Gündüz2026-03-281-0/+465