| Commit message (Collapse) | Author | Files | Lines | ||
|---|---|---|---|---|---|
| 2026-06-14 | gitignore: track new binary and library names | Onur Gündüz | 1 | -825/+0 | |
| 2026-06-14 | kernels: drop asr_ prefix naming | Onur Gündüz | 1 | -2/+2 | |
| 2026-06-14 | cli: rename flags, add --stream, split serving into pplx-embed-server | Onur Gündüz | 1 | -203/+42 | |
| 2026-06-14 | cuda: add optional BF16 CUDA weight storage (--cuda-weights bf16) | Onur Gündüz | 1 | -0/+30 | |
| 2026-06-14 | cuda: add fast GEMM mode (--cuda-fast-gemm mode) | Onur Gündüz | 1 | -0/+25 | |
| 2026-06-14 | cuda: add server contextual path | Onur Gündüz | 1 | -6/+2 | |
| 2026-06-14 | cuda: add initial CUDA embedding backend | Onur Gündüz | 1 | -9/+71 | |
| 2026-06-14 | chore: address static analyzer warnings | Onur Gündüz | 1 | -4/+5 | |
| 2026-06-14 | tokenizer: add reusable encode workspace | Onur Gündüz | 1 | -1/+18 | |
| 2026-06-14 | dist: add fp16 activation transport | Onur Gündüz | 1 | -0/+21 | |
| 2026-06-14 | mlx: add opt-in 8-bit weight quantization | Onur Gündüz | 1 | -7/+53 | |
| 2026-06-14 | server: reject unsafe mlx model overcommit | Onur Gündüz | 1 | -0/+7 | |
| 2026-06-14 | server: batch standard requests by token budget | Onur Gündüz | 1 | -0/+12 | |
| 2026-06-14 | dist: add direct two-node fp32 inference | Onur Gündüz | 1 | -18/+123 | |
| 2026-06-14 | server: add embeddings micro-batching | Onur Gündüz | 1 | -2/+14 | |
| 2026-06-14 | server: implement HTTP API with libae integration | Onur Gündüz | 1 | -22/+161 | |
| 2026-06-14 | server: report workspace memory | Onur Gündüz | 1 | -3/+11 | |
| 2026-06-14 | api: simplify embedding API | Onur Gündüz | 1 | -7/+25 | |
| 2026-06-14 | api: split model and workspace ownership | Onur Gündüz | 1 | -1/+1 | |
| 2026-06-14 | all: support batched embedding attention | Onur Gündüz | 1 | -70/+213 | |
| 2026-03-28 | Refactor and enhance pplx_embed and pplx_embed_mlx for improved model support | Onur Gündüz | 1 | -249/+230 | |
| - 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 | |||||
| 2026-03-28 | Init | Onur Gündüz | 1 | -0/+363 | |
