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). @ aarch64-docker

AlpinDale 92cee435e2 rocm: add more quants, fix _scaled_mm call (#1062)		hai 1 mes
..
__init__.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 2 meses
fp6_utils.py	73177656ed feat: quant_llm support (#755)	hai 4 meses
layer_utils.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 2 meses
machete_utils.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 2 meses
marlin_utils.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 2 meses
marlin_utils_fp8.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 5 meses
marlin_utils_test.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 5 meses
marlin_utils_test_24.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 5 meses
marlin_utils_test_qqq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 5 meses
quant_utils.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	hai 2 meses
w8a8_utils.py	92cee435e2 rocm: add more quants, fix _scaled_mm call (#1062)	hai 1 mes