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). @ 9bbc75d2e3389428a587af92f60e94482898ae15

AlpinDale 9bbc75d2e3 wip		vor 6 Monaten
..
__init__.py	5884e0b904 add bitnetforcausallm support	vor 6 Monaten
arctic.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
baichuan.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
bitnet.py	9bbc75d2e3 wip	vor 6 Monaten
bloom.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
chatglm.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
commandr.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
dbrx.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
decilm.py	50b7c13db0 refactor: attention selector (#552)	vor 6 Monaten
deepseek.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
falcon.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
gemma.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
gpt2.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
gpt_bigcode.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
gpt_j.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
gpt_neox.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
internlm2.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
jais.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
llama.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 6 Monaten
llama_embedding.py	50b7c13db0 refactor: attention selector (#552)	vor 6 Monaten
llava.py	24a2d9c2c8 minor llava refactoring	vor 6 Monaten
minicpm.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
mixtral.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 6 Monaten
mixtral_quant.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 6 Monaten
mpt.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
olmo.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
opt.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
orion.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
phi.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
phi3_small.py	696f2cd59c add phi3_small support with blocksparse attention	vor 6 Monaten
qwen.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
qwen2.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 6 Monaten
qwen2_moe.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
stablelm.py	656459fd84 make fp8_e4m3 work on nvidia	vor 6 Monaten
starcoder2.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 6 Monaten
vlm_base.py	f970f3f3fb add base class for VLMs	vor 6 Monaten
xverse.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 6 Monaten