david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ rc_054

AlpinDale c1c37c755d bump version to 0.6.0		4 bulan lalu
..
adapter_commons	6b1fdd07bd chore: add isort and refactor formatting script and utils	4 bulan lalu
attention	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
common	2b85ffb1a5 chore: minor cleanups	4 bulan lalu
distributed	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
endpoints	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
engine	28946766fb fix: allow loading GGUF model without .gguf extension	4 bulan lalu
executor	87694c8aba feat: add RPC server and client via ZMQ (#615)	4 bulan lalu
inputs	1ab2dad198 Refactor prompt processing (#605)	4 bulan lalu
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	10 bulan lalu
lora	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
modeling	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
multimodal	705e50f4bd fix: broadcasting logic for multi_modal_kwargs	4 bulan lalu
platforms	a3e26391e4 chore: add a wrapper for torch.inference_mode decorator	4 bulan lalu
processing	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
prompt_adapter	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
quantization	208cd5405f fix: cpu offloading with gptq	4 bulan lalu
server	040e5af52b refactor: factor out code for running uvicorn again	4 bulan lalu
spec_decode	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
task_handler	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
transformers_utils	28946766fb fix: allow loading GGUF model without .gguf extension	4 bulan lalu
triton_utils	4d4e767838 ci: take one of fixing lint issues	4 bulan lalu
__init__.py	0c17c2a8a7 chore: add commit hash, clean up engine logs	4 bulan lalu
_core_ext.py	141672a0d4 kernels: disambiguate quantized types via a new ScalarType	4 bulan lalu
_custom_ops.py	0e6c400b13 feat: re-add GGUF (#600)	4 bulan lalu
_ipex_ops.py	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	4 bulan lalu
py.typed	1c988a48b2 fix logging and add py.typed	1 tahun lalu
scalar_type.py	141672a0d4 kernels: disambiguate quantized types via a new ScalarType	4 bulan lalu
version.py	c1c37c755d bump version to 0.6.0	4 bulan lalu