aboutsummaryrefslogtreecommitdiff
path: root/README.md (unfollow)
Commit message (Collapse)AuthorFilesLines
2026-07-14docs: update README introHEADv0.3.0masterOnur Gündüz1-19/+9
2026-07-14chore: move the server README to top-levelOnur Gündüz1-18/+263
2026-07-14chore: update READMEOnur Gündüz1-26/+0
2026-06-30docs: update READMEOnur Gündüz1-1/+2
2026-06-30docs: update READMEOnur Gündüz1-23/+38
2026-06-28docs: fix heading sizeOnur Gündüz1-1/+1
2026-06-28docs: update READMEOnur Gündüz1-13/+29
2026-06-27chore: update README.mdOnur Gündüz1-11/+16
2026-06-25chore: update READMEOnur Gündüz1-13/+20
2026-06-25all: migrate to yyjsonOnur Gündüz1-5/+2
2026-06-21docs: update README.mdOnur Gündüz1-272/+35
2026-06-18server: serve models by explicit labelsOnur Gündüz1-73/+46
2026-06-17chore: document XLM-R models, F16 weights, and config-driven poolingOnur Gündüz1-24/+32
2026-06-16chore: document supported models and backends in READMEOnur Gündüz1-8/+53
2026-06-15cli: add --json output, plain matrix, and version flagsOnur Gündüz1-2/+21
2026-06-15server: document HTTP API and add openapi.yaml specOnur Gündüz1-44/+164
2026-06-14server: per-family embedding encoding (Qwen3 float, pplx int8)Onur Gündüz1-0/+6
2026-06-14server: add Qwen3-Embedding-8B model slotOnur Gündüz1-2/+2
2026-06-14all: add Qwen3-Embedding-4B + fix terminal tokenOnur Gündüz1-2/+4
2026-06-14docs: add acknowledgements to READMEOnur Gündüz1-0/+15
2026-06-14all: add support for Qwen3-Embedding + causal GQA attentionOnur Gündüz1-3/+21
2026-06-14docs: update README with the model support and usage examplesOnur Gündüz1-3/+62
2026-06-14build: add gpu target for auto-selecting backendOnur Gündüz1-193/+14
2026-06-14kernels: drop asr_ prefix namingOnur Gündüz1-1/+1
2026-03-29Update README.mdv0.1.0Onur Gündüz1-35/+103
2026-03-28Add benchmark scriptOnur Gündüz1-0/+46
2026-03-28Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz1-1/+87
- 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