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). @ feat/tree-attention

sgsdxzy a3b1602391 fix: rope scaling for cohere and qwen (#436)		8 months ago
..
__init__.py	c2aaaefd57 allow out-of-tree model registry	9 months ago
baichuan.py	50c2434267 move megatron to a top-level directory	9 months ago
bloom.py	50c2434267 move megatron to a top-level directory	9 months ago
chatglm.py	50c2434267 move megatron to a top-level directory	9 months ago
cohere.py	a3b1602391 fix: rope scaling for cohere and qwen (#436)	8 months ago
dbrx.py	50c2434267 move megatron to a top-level directory	9 months ago
decilm.py	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	10 months ago
deepseek.py	50c2434267 move megatron to a top-level directory	9 months ago
falcon.py	50c2434267 move megatron to a top-level directory	9 months ago
gemma.py	0d0c6b313c fix: linear bias of qkv layers in models (#430)	8 months ago
gpt2.py	50c2434267 move megatron to a top-level directory	9 months ago
gpt_bigcode.py	50c2434267 move megatron to a top-level directory	9 months ago
gpt_j.py	50c2434267 move megatron to a top-level directory	9 months ago
gpt_neox.py	50c2434267 move megatron to a top-level directory	9 months ago
internlm2.py	50c2434267 move megatron to a top-level directory	9 months ago
llama.py	0d0c6b313c fix: linear bias of qkv layers in models (#430)	8 months ago
llava.py	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	9 months ago
mixtral.py	50c2434267 move megatron to a top-level directory	9 months ago
mpt.py	50c2434267 move megatron to a top-level directory	9 months ago
olmo.py	50c2434267 move megatron to a top-level directory	9 months ago
opt.py	50c2434267 move megatron to a top-level directory	9 months ago
phi.py	50c2434267 move megatron to a top-level directory	9 months ago
qwen.py	a3b1602391 fix: rope scaling for cohere and qwen (#436)	8 months ago
qwen2.py	a3b1602391 fix: rope scaling for cohere and qwen (#436)	8 months ago
qwen2moe.py	a3b1602391 fix: rope scaling for cohere and qwen (#436)	8 months ago
stablelm.py	0d0c6b313c fix: linear bias of qkv layers in models (#430)	8 months ago