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). @ deepseek_v3

AlpinDale cec4da1dab quants: support w8a8 fp8 block-wise quantization from DS3		4 settimane fa
..
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
allclose_default.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
conftest.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
quant_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_activation.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_attention.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_attention_selector.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_awq_triton.py	fcfcfc65e1 quants: add triton kernels for AWQ (#946)	1 mese fa
test_block_fp8.py	cec4da1dab quants: support w8a8 fp8 block-wise quantization from DS3	4 settimane fa
test_blocksparse_attention.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_cache.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_causal_conv1d.py	a90d41d908 tests: add kernel tests for causal_conv1d and mamba_ssm (#947)	1 mese fa
test_cutlass.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_encoder_decoder_attn.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_flash_attn.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_flashinfer.py	a62f0925fe update flashinfer test (#945)	1 mese fa
test_fp8_quant.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_int8_quant.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_layernorm.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_machete_gemm.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_mamba_ssm.py	a90d41d908 tests: add kernel tests for causal_conv1d and mamba_ssm (#947)	1 mese fa
test_marlin_gemm.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa
test_moe.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_permute_cols.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	1 mese fa
test_pos_encoding.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_prefix_prefill.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_rand.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_sampler.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
utils.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 settimane fa