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). @ uneven-head-size-flashinfer

AlpinDale 2d7929d3b7 fix: flashinfer crash with uneven attention group_size		hai 1 mes
..
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
allclose_default.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
conftest.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
quant_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_activation.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_attention.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_attention_selector.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_blocksparse_attention.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_cache.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_cutlass.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_encoder_decoder_attn.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_flash_attn.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_flashinfer.py	2d7929d3b7 fix: flashinfer crash with uneven attention group_size	hai 1 mes
test_fp8_quant.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_int8_quant.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_layernorm.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_machete_gemm.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 1 mes
test_marlin_gemm.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_moe.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_permute_cols.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 1 mes
test_pos_encoding.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_prefix_prefill.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_rand.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_sampler.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes