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