Home Verkennen Help
Registreren Inloggen
david
/
aphrodite-engine
spiegel van https://github.com/PygmalionAI/aphrodite-engine
1
0
Vork 0
Bestanden Issues 0 Wiki
Aftakking: bitnet
Aftakkingen Labels
aphrodite-engin...
/
aphrodite
/
modeling
/
models
AlpinDale 9bbc75d2e3 wip 6 maanden geleden
..
__init__.py 5884e0b904 add bitnetforcausallm support 6 maanden geleden
arctic.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
baichuan.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
bitnet.py 9bbc75d2e3 wip 6 maanden geleden
bloom.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
chatglm.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
commandr.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
dbrx.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
decilm.py 50b7c13db0 refactor: attention selector (#552) 6 maanden geleden
deepseek.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
falcon.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
gemma.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
gpt2.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
gpt_bigcode.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
gpt_j.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
gpt_neox.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
internlm2.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
jais.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
llama.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 6 maanden geleden
llama_embedding.py 50b7c13db0 refactor: attention selector (#552) 6 maanden geleden
llava.py 24a2d9c2c8 minor llava refactoring 6 maanden geleden
minicpm.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
mixtral.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 6 maanden geleden
mixtral_quant.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 6 maanden geleden
mpt.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
olmo.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
opt.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
orion.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
phi.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
phi3_small.py 696f2cd59c add phi3_small support with blocksparse attention 6 maanden geleden
qwen.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
qwen2.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 6 maanden geleden
qwen2_moe.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
stablelm.py 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
starcoder2.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 6 maanden geleden
vlm_base.py f970f3f3fb add base class for VLMs 6 maanden geleden
xverse.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 6 maanden geleden