| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | gitignore: track new binary and library names | Onur Gündüz | 2026-06-14 | 1 | -293/+0 |
| | | |||||
| * | late: add packed maxsim scoring | Onur Gündüz | 2026-06-14 | 1 | -0/+12 |
| | | |||||
| * | late: add CPU token vectors and maxsim | Onur Gündüz | 2026-06-14 | 1 | -0/+35 |
| | | |||||
| * | server: simplify context separator logic | Onur Gündüz | 2026-06-14 | 1 | -0/+1 |
| | | |||||
| * | server: batch contextual document inference | Onur Gündüz | 2026-06-14 | 1 | -0/+17 |
| | | |||||
| * | dist: load distributed layer shards selectively | Onur Gündüz | 2026-06-14 | 1 | -0/+12 |
| | | |||||
| * | dist: add distributed layer-slice foundation | Onur Gündüz | 2026-06-14 | 1 | -0/+31 |
| | | |||||
| * | api: add opt-in l2 normalization helper | Onur Gündüz | 2026-06-14 | 1 | -0/+9 |
| | | |||||
| * | server: align embedding quantization with perplexity | Onur Gündüz | 2026-06-14 | 1 | -5/+8 |
| | | |||||
| * | server: implement HTTP API with libae integration | Onur Gündüz | 2026-06-14 | 1 | -0/+25 |
| | | |||||
| * | server: report workspace memory | Onur Gündüz | 2026-06-14 | 1 | -0/+8 |
| | | |||||
| * | cpu: support BF16 weights | Onur Gündüz | 2026-06-14 | 1 | -1/+1 |
| | | |||||
| * | api: simplify embedding API | Onur Gündüz | 2026-06-14 | 1 | -90/+12 |
| | | |||||
| * | api: split model and workspace ownership | Onur Gündüz | 2026-06-14 | 1 | -5/+47 |
| | | |||||
| * | all: support batched embedding attention | Onur Gündüz | 2026-06-14 | 1 | -0/+31 |
| | | |||||
| * | Refactor and enhance pplx_embed and pplx_embed_mlx for improved model support | Onur Gündüz | 2026-03-28 | 1 | -94/+53 |
| | | | | | | | | | | | | | - 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 | ||||
| * | Init | Onur Gündüz | 2026-03-28 | 1 | -0/+186 |
