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).

AlpinDale 7b6501bd05 tests: refactor model tests (#1078)		2 dní pred
..
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
allclose_default.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
conftest.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
quant_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_activation.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 týždeň pred
test_attention.py	61aed092a5 rocm: add support for FP8 KV cache in the custom paged attention kkernels (#1066)	5 dní pred
test_attention_selector.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_awq_triton.py	fcfcfc65e1 quants: add triton kernels for AWQ (#946)	2 týždňov pred
test_blocksparse_attention.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_cache.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 týždeň pred
test_causal_conv1d.py	9bdf8d5bfa mamba: enable continuous batching for mamba kernels (#1055)	1 týždeň pred
test_cutlass.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 týždeň pred
test_encoder_decoder_attn.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_flash_attn.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_flashinfer.py	a62f0925fe update flashinfer test (#945)	2 týždňov pred
test_fp8_quant.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_int8_quant.py	8976805f90 kernel: asymmetric AQ AZP quantization kernels (#1048)	1 týždeň pred
test_layernorm.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 týždeň pred
test_machete_gemm.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 týždeň pred
test_mamba_ssm.py	9bdf8d5bfa mamba: enable continuous batching for mamba kernels (#1055)	1 týždeň pred
test_marlin_gemm.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 týždeň pred
test_moe.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_permute_cols.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	1 mesiac pred
test_pos_encoding.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
test_prefix_prefill.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
utils.py	7b6501bd05 tests: refactor model tests (#1078)	2 dní pred