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). @ dry-fix

AlpinDale 93bc863591 feat: Machete Kernels for Hopper GPUs (#842)		1 mese fa
..
async_aphrodite	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
basic_correctness	2f61644f6e SPMD optimizations (#824)	1 mese fa
benchmarks	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	1 mese fa
compile	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
core	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 mese fa
distributed	2f61644f6e SPMD optimizations (#824)	1 mese fa
endpoints	262cbc63b7 fix: vision api test template path	1 mese fa
engine	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
kernels	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	1 mese fa
lora	68f050129d fix: lora worker manager test import	1 mese fa
metrics	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
modeling	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
models	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
multi_step	48a8693aed feat: multi-step scheduling (#831)	1 mese fa
multimodal	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
plugins	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
prefix_caching	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 mese fa
prompt_adapter	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
prompts	e1f3fd1e02 fix: test units (#201)	1 anno fa
quantization	7f1c9af5e2 fix: fp8 quant test	1 mese fa
samplers	60f7b828d5 feat: add skew sampling (#834)	1 mese fa
spec_decode	16b587c104 fix: hidden states handling in batch expansion for spec decoding (#839)	1 mese fa
tensorizer_loader	32a37e8107 tests: partially fix tensorizer and logprobs tests	1 mese fa
tokenization	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
weight_loading	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
worker	48a8693aed feat: multi-step scheduling (#831)	1 mese fa
__init__.py	2755a48d51 merge dev branch into main (#153)	1 anno fa
conftest.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_cache_block_hashing.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_config.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_embedded_commit.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_inputs.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_logits_processor.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_regression.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_sampling_params.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_scalartype.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_sequence.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_sharded_state_loader.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa