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). @ update_benchmarks

AlpinDale f98e7b2f8c feat: add HQQ quantization support (#795)		преди 2 месеца
..
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
fp6_utils.py	73177656ed feat: quant_llm support (#755)	преди 4 месеца
marlin_utils.py	f98e7b2f8c feat: add HQQ quantization support (#795)	преди 2 месеца
marlin_utils_fp8.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
marlin_utils_test.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
marlin_utils_test_24.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
marlin_utils_test_qqq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
quant_utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
w8a8_utils.py	b0f262eec1 feat: FP8 quantization support for AMD ROCm (#729)	преди 4 месеца