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). @ sampler_refactor

AlpinDale 1225c4dfd6 fix: illegal mem access crash for marlin		6 hónapja
..
all_reduce	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
attention	fca911ee0a vLLM Upstream Sync (#526)	6 hónapja
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 hónapja
cpu	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	11 hónapja
moe	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
punica	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
quantization	1225c4dfd6 fix: illegal mem access crash for marlin	6 hónapja
activation_kernels.cu	3d6695cfbb feat: add approximate gelu activation kernels (#370)	9 hónapja
cache.h	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
cache_kernels.cu	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
cuda_compat.h	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
cuda_utils.h	31c95011a6 feat: FP8 E5M2 KV Cache (#226)	11 hónapja
cuda_utils_kernels.cu	31c95011a6 feat: FP8 E5M2 KV Cache (#226)	11 hónapja
dispatch_utils.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 hónapja
layernorm_kernels.cu	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
ops.h	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
pos_encoding_kernels.cu	e702f587cf feat: add batched RoPE kernels (#371)	9 hónapja
pybind.cpp	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
reduction.cuh	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja