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). @ c50309d3867c8fd0e7310abba4e65087defa4297

AlpinDale 03bd85c950 chore: multi-image support for llava-next (#935)		пре 2 месеци
..
async_aphrodite	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
basic_correctness	f7f3fed265 feat: add async postprocessor (#925)	пре 2 месеци
benchmarks	f7f3fed265 feat: add async postprocessor (#925)	пре 2 месеци
compile	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
core	f7f3fed265 feat: add async postprocessor (#925)	пре 2 месеци
distributed	d69273bd2b ray: better error when placement group topology is incorrect (#906)	пре 3 месеци
endpoints	0c162c8dad api: use fp32 for base64 embeddings (#919)	пре 2 месеци
engine	f7f3fed265 feat: add async postprocessor (#925)	пре 2 месеци
kernels	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	пре 3 месеци
lora	68f050129d fix: lora worker manager test import	пре 3 месеци
metrics	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
modeling	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
models	03bd85c950 chore: multi-image support for llava-next (#935)	пре 2 месеци
multi_step	f7f3fed265 feat: add async postprocessor (#925)	пре 2 месеци
multimodal	03bd85c950 chore: multi-image support for llava-next (#935)	пре 2 месеци
plugins	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
prefix_caching	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	пре 3 месеци
prompt_adapter	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
prompts	e1f3fd1e02 fix: test units (#201)	пре 1 година
quantization	7f1c9af5e2 fix: fp8 quant test	пре 3 месеци
samplers	2150bb5019 sampler: add range parameter for DRY (#855)	пре 3 месеци
spec_decode	3b684a8a54 spec decode: streamline batch expansion tensor manipulation (#918)	пре 2 месеци
tensorizer_loader	673621a3d2 xpu: refactor the model runner for tensor parallelism (#910)	пре 2 месеци
tokenization	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
tpu	436d8fa0f1 core: do not compile for profiling (#931)	пре 2 месеци
weight_loading	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
worker	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	пре 3 месеци
__init__.py	2755a48d51 merge dev branch into main (#153)	пре 1 година
conftest.py	03bd85c950 chore: multi-image support for llava-next (#935)	пре 2 месеци
test_cache_block_hashing.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_config.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_embedded_commit.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_inputs.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_logits_processor.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_regression.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_sampling_params.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_scalartype.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_sequence.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_sharded_state_loader.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
test_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	пре 3 месеци