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). @ bitnet

AlpinDale 9bbc75d2e3 wip		hace 5 meses
..
__init__.py	5884e0b904 add bitnetforcausallm support	hace 5 meses
arctic.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
baichuan.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
bitnet.py	9bbc75d2e3 wip	hace 5 meses
bloom.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
chatglm.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
commandr.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
dbrx.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
decilm.py	50b7c13db0 refactor: attention selector (#552)	hace 6 meses
deepseek.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
falcon.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
gemma.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
gpt2.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
gpt_bigcode.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
gpt_j.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
gpt_neox.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
internlm2.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
jais.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
llama.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	hace 5 meses
llama_embedding.py	50b7c13db0 refactor: attention selector (#552)	hace 6 meses
llava.py	24a2d9c2c8 minor llava refactoring	hace 6 meses
minicpm.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
mixtral.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	hace 5 meses
mixtral_quant.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	hace 5 meses
mpt.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
olmo.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
opt.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
orion.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
phi.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
phi3_small.py	696f2cd59c add phi3_small support with blocksparse attention	hace 5 meses
qwen.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
qwen2.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	hace 5 meses
qwen2_moe.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
stablelm.py	656459fd84 make fp8_e4m3 work on nvidia	hace 6 meses
starcoder2.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	hace 5 meses
vlm_base.py	f970f3f3fb add base class for VLMs	hace 6 meses
xverse.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	hace 5 meses