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). @ spmd-optimization

AlpinDale 22428c777d fix import in spec decode e2e integration test		2 mesiacov pred
..
async_aphrodite	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
basic_correctness	2242da8b59 update	2 mesiacov pred
benchmarks	ee5964465d chore: max_num_seqs in throughput benchmark (#770)	3 mesiacov pred
compile	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
core	2242da8b59 update	2 mesiacov pred
distributed	2242da8b59 update	2 mesiacov pred
endpoints	262cbc63b7 fix: vision api test template path	2 mesiacov pred
engine	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
kernels	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
lora	68f050129d fix: lora worker manager test import	2 mesiacov pred
metrics	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
modeling	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
models	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
multimodal	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
plugins	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
prefix_caching	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
prompt_adapter	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
prompts	e1f3fd1e02 fix: test units (#201)	1 rok pred
quantization	7f1c9af5e2 fix: fp8 quant test	2 mesiacov pred
samplers	2242dcbcf2 fix: circular import	2 mesiacov pred
spec_decode	22428c777d fix import in spec decode e2e integration test	2 mesiacov pred
tensorizer_loader	32a37e8107 tests: partially fix tensorizer and logprobs tests	2 mesiacov pred
tokenization	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
weight_loading	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
worker	2242dcbcf2 fix: circular import	2 mesiacov pred
__init__.py	2755a48d51 merge dev branch into main (#153)	1 rok pred
conftest.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_cache_block_hashing.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_config.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_embedded_commit.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_inputs.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_logits_processor.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_regression.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_sampling_params.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_scalartype.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_sequence.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_sharded_state_loader.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
test_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesiacov pred