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