aboutsummaryrefslogtreecommitdiff
path: root/Makefile (follow)
Commit message (Collapse)AuthorAgeFilesLines
* all: add support for Qwen3-Embedding + causal GQA attentionOnur Gündüz2026-06-141-1/+10
|
* docs: fix benchstat.py path in commentsOnur Gündüz2026-06-141-2/+2
|
* build: add gpu target for auto-selecting backendOnur Gündüz2026-06-141-11/+21
|
* build: add test-safetensors to PHONY targetsOnur Gündüz2026-06-141-2/+2
|
* build: add test-bf16 and test-safetensors targets to MakefileOnur Gündüz2026-06-141-1/+12
|
* chore: rename projectOnur Gündüz2026-06-141-17/+11
|
* chore: comments housekeepingOnur Gündüz2026-06-141-16/+11
|
* dist: remove distributed layer-sharding (protocol, CLI flags, slice APIs)Onur Gündüz2026-06-141-7/+3
|
* build: fix test_cli -lm on Linux, annotate CUDA API exportsOnur Gündüz2026-06-141-3/+3
|
* build: target the local GPU with -arch=native in the nvcc ruleOnur Gündüz2026-06-141-1/+3
|
* build: export only the public API from the shared libraryOnur Gündüz2026-06-141-1/+3
|
* bench: progress output during sampling, ignore .gitignore in dirty stampOnur Gündüz2026-06-141-1/+3
|
* bench: regression microbenchmarks with benchstat compareOnur Gündüz2026-06-141-1/+28
|
* build: backend targets produce static and shared libraries, drop make libOnur Gündüz2026-06-141-20/+10
|
* tests: cover the late-interaction API and the CLI binaryOnur Gündüz2026-06-141-1/+21
|
* build: relative paths and richer HTML in make coverageOnur Gündüz2026-06-141-7/+19
|
* tests: make test_workspace hermetic, add it to make testOnur Gündüz2026-06-141-2/+10
|
* build: add make coverage (clang source-based, llvm-cov)Onur Gündüz2026-06-141-16/+74
|
* build: rename make targets blas->cpu, mlx->metal, shared->libOnur Gündüz2026-06-141-22/+22
|
* tests: hermetic BPE tokenizer test with fast/slow path equalityOnur Gündüz2026-06-141-0/+4
|
* tests: add server encoder unit tests via EMBED_SERVER_TEST includeOnur Gündüz2026-06-141-1/+8
|
* tests: make safetensors and bf16-model tests hermetic, join make testOnur Gündüz2026-06-141-1/+9
|
* tests,bench: move generated C checkers into standing filesOnur Gündüz2026-06-141-1/+6
|
* chore: rename sources; binaries pplx-embed, pplx-embed-serverOnur Gündüz2026-06-141-26/+23
|
* kernels: drop asr_ prefix namingOnur Gündüz2026-06-141-19/+19
|
* cli: rename flags, add --stream, split serving into pplx-embed-serverOnur Gündüz2026-06-141-11/+44
|
* build: produce libpplxembed.a and a shared-library targetOnur Gündüz2026-06-141-5/+38
|
* build: allow FP reassociation/contraction, keep finite-math offOnur Gündüz2026-06-141-3/+7
|
* cuda: add initial CUDA embedding backendOnur Gündüz2026-06-141-2/+20
|
* kernels: fix OpenBLAS thread contention and numerical instabilityOnur Gündüz2026-06-141-1/+3
|
* build: add address/undefined sanitizers to debug buildsOnur Gündüz2026-06-141-2/+4
|
* dist: add direct two-node fp32 inferenceOnur Gündüz2026-06-141-1/+5
|
* server: implement HTTP API with libae integrationOnur Gündüz2026-06-141-5/+26
|
* Refactor and enhance pplx_embed and pplx_embed_mlx for improved model supportOnur Gündüz2026-03-281-10/+3
| | | | | | | | | | | | - 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/+128