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). @ sampling_kernels

AlpinDale 22422d962b feat: add cuda sampling kernels for top_k and top_p		1 mēnesi atpakaļ
..
async_aphrodite	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
basic_correctness	2f61644f6e SPMD optimizations (#824)	1 mēnesi atpakaļ
benchmarks	22422d962b feat: add cuda sampling kernels for top_k and top_p	1 mēnesi atpakaļ
compile	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
core	2f61644f6e SPMD optimizations (#824)	1 mēnesi atpakaļ
distributed	2f61644f6e SPMD optimizations (#824)	1 mēnesi atpakaļ
endpoints	262cbc63b7 fix: vision api test template path	1 mēnesi atpakaļ
engine	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
kernels	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
lora	68f050129d fix: lora worker manager test import	1 mēnesi atpakaļ
metrics	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
modeling	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
models	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
multimodal	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
plugins	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
prefix_caching	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
prompt_adapter	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
prompts	e1f3fd1e02 fix: test units (#201)	1 gadu atpakaļ
quantization	7f1c9af5e2 fix: fp8 quant test	1 mēnesi atpakaļ
samplers	22427602eb feat: add top-nsigma sampling method	1 mēnesi atpakaļ
spec_decode	2f61644f6e SPMD optimizations (#824)	1 mēnesi atpakaļ
tensorizer_loader	32a37e8107 tests: partially fix tensorizer and logprobs tests	1 mēnesi atpakaļ
tokenization	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
weight_loading	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
worker	2f61644f6e SPMD optimizations (#824)	1 mēnesi atpakaļ
__init__.py	2755a48d51 merge dev branch into main (#153)	1 gadu atpakaļ
conftest.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_cache_block_hashing.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_config.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_embedded_commit.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_inputs.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_logits_processor.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_regression.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_sampling_params.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_scalartype.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_sequence.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_sharded_state_loader.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
test_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mēnesi atpakaļ