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). @ 561588d97d7cca90ed7fcdb936650046d0493c91

AlpinDale 561588d97d wip		4 ماه پیش
..
adapter_commons	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
attention	5d37ec1016 suppress tpu import warning (#696)	4 ماه پیش
common	28b6397188 chore: quant config for speculative draft models (#719)	4 ماه پیش
distributed	8878e3a63f fix: import ray under a guard (#708)	4 ماه پیش
endpoints	561588d97d wip	4 ماه پیش
engine	28b6397188 chore: quant config for speculative draft models (#719)	4 ماه پیش
executor	008e646c7e chore: add support for up to 2048 block size (#715)	4 ماه پیش
inputs	0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712)	4 ماه پیش
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	10 ماه پیش
lora	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 ماه پیش
modeling	561588d97d wip	4 ماه پیش
multimodal	0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712)	4 ماه پیش
platforms	5d37ec1016 suppress tpu import warning (#696)	4 ماه پیش
plugins	f76f2a5af0 feat: add aphrodite plugin system (#705)	4 ماه پیش
processing	577586309d chore: multi-step args and sequence modifications (#713)	4 ماه پیش
prompt_adapter	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
quantization	04da8c33bd Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706)	4 ماه پیش
server	ed9a6f97c1 fix: kill api server when pinging dead engine (#660)	4 ماه پیش
spec_decode	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 ماه پیش
task_handler	008e646c7e chore: add support for up to 2048 block size (#715)	4 ماه پیش
transformers_utils	d5033e12fd feat: implement mistral tokenizer mode (#711)	4 ماه پیش
triton_utils	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
_core_ext.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
_custom_ops.py	5d37ec1016 suppress tpu import warning (#696)	4 ماه پیش
_ipex_ops.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
py.typed	1c988a48b2 fix logging and add py.typed	1 سال پیش
scalar_type.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 ماه پیش
version.py	8e0d376f1c ci: bump aphrodite to 0.6.1 (#722)	4 ماه پیش