aboutsummaryrefslogtreecommitdiff
path: root/main.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* gitignore: track new binary and library namesOnur Gündüz2026-06-141-825/+0
|
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-141-2/+2
|
* cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz2026-06-141-203/+42
|
* cuda: add optional BF16 CUDA weight storage (--cuda-weights bf16)Onur Gündüz2026-06-141-0/+30
|
* cuda: add fast GEMM mode (--cuda-fast-gemm mode)Onur Gündüz2026-06-141-0/+25
|
* cuda: add server contextual pathOnur Gündüz2026-06-141-6/+2
|
* cuda: add initial CUDA embedding backendOnur Gündüz2026-06-141-9/+71
|
* chore: address static analyzer warningsOnur Gündüz2026-06-141-4/+5
|
* tokenizer: add reusable encode workspaceOnur Gündüz2026-06-141-1/+18
|
* dist: add fp16 activation transportOnur Gündüz2026-06-141-0/+21
|
* mlx: add opt-in 8-bit weight quantizationOnur Gündüz2026-06-141-7/+53
|
* server: reject unsafe mlx model overcommitOnur Gündüz2026-06-141-0/+7
|
* server: batch standard requests by token budgetOnur Gündüz2026-06-141-0/+12
|
* dist: add direct two-node fp32 inferenceOnur Gündüz2026-06-141-18/+123
|
* server: add embeddings micro-batchingOnur Gündüz2026-06-141-2/+14
|
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-141-22/+161
|
* server: report workspace memoryOnur Gündüz2026-06-141-3/+11
|
* api: simplify embedding APIOnur Gündüz2026-06-141-7/+25
|
* api: split model and workspace ownershipOnur Gündüz2026-06-141-1/+1
|
* all: support batched embedding attentionOnur Gündüz2026-06-141-70/+213
|
* Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz2026-03-281-249/+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
* InitOnur Gündüz2026-03-281-0/+363