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). @ c3a221eb02eea2198814a6e06011748e170c0ac5

AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)		1 年之前
..
quantization	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	1 年之前
triton_kernel	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 年之前
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 年之前
activation.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 年之前
attention.py	31c95011a6 feat: FP8 E5M2 KV Cache (#226)	1 年之前
layernorm.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 年之前
linear.py	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	1 年之前
rejection.py	95bdd35ec9 feat: rejection sampler (#197)	1 年之前
rotary_embedding.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 年之前
sampler.py	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	1 年之前
vocab_parallel_embedding.py	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	1 年之前