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). @ profile_no_compile

AlpinDale b0a8169b54 core: do not compile for profiling		1 mēnesi atpakaļ
..
async_aphrodite	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
basic_correctness	f7f3fed265 feat: add async postprocessor (#925)	1 mēnesi atpakaļ
benchmarks	f7f3fed265 feat: add async postprocessor (#925)	1 mēnesi atpakaļ
compile	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
core	f7f3fed265 feat: add async postprocessor (#925)	1 mēnesi atpakaļ
distributed	d69273bd2b ray: better error when placement group topology is incorrect (#906)	1 mēnesi atpakaļ
endpoints	0c162c8dad api: use fp32 for base64 embeddings (#919)	1 mēnesi atpakaļ
engine	f7f3fed265 feat: add async postprocessor (#925)	1 mēnesi atpakaļ
kernels	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	1 mēnesi atpakaļ
lora	68f050129d fix: lora worker manager test import	2 mēneši atpakaļ
metrics	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
modeling	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
models	fce970a846 feat: multi-image input support for Phi3V (#917)	1 mēnesi atpakaļ
multi_step	f7f3fed265 feat: add async postprocessor (#925)	1 mēnesi atpakaļ
multimodal	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
plugins	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
prefix_caching	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	2 mēneši atpakaļ
prompt_adapter	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
prompts	e1f3fd1e02 fix: test units (#201)	1 gadu atpakaļ
quantization	7f1c9af5e2 fix: fp8 quant test	2 mēneši atpakaļ
samplers	2150bb5019 sampler: add range parameter for DRY (#855)	1 mēnesi atpakaļ
spec_decode	3b684a8a54 spec decode: streamline batch expansion tensor manipulation (#918)	1 mēnesi atpakaļ
tensorizer_loader	673621a3d2 xpu: refactor the model runner for tensor parallelism (#910)	1 mēnesi atpakaļ
tokenization	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
tpu	b0a8169b54 core: do not compile for profiling	1 mēnesi atpakaļ
weight_loading	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
worker	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	1 mēnesi atpakaļ
__init__.py	2755a48d51 merge dev branch into main (#153)	1 gadu atpakaļ
conftest.py	653d1a08d4 feat: add support for audio models (#891)	1 mēnesi atpakaļ
test_cache_block_hashing.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_config.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_embedded_commit.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_inputs.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_logits_processor.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_regression.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_sampling_params.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_scalartype.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_sequence.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_sharded_state_loader.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
test_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mēneši atpakaļ