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