.. |
__init__.py
|
adb6982090
models: add support for IBM Granite (PowerLM) models (#978)
|
2 주 전 |
arctic.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
baichuan.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
bart.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
blip.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
blip2.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
bloom.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
chameleon.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
chatglm.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
clip.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
commandr.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
dbrx.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
decilm.py
|
9022c6d869
remove progress_bar imports
|
2 달 전 |
deepseek.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
deepseek_v2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
eagle.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
exaone.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
falcon.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
fuyu.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
gemma.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
gemma2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
gpt2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
gpt_bigcode.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
gpt_j.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
gpt_neox.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
granite.py
|
adb6982090
models: add support for IBM Granite (PowerLM) models (#978)
|
2 주 전 |
idefics2_vision_model.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
interfaces.py
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
4 달 전 |
intern_vit.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
internlm2.py
|
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)
|
2 주 전 |
internvl.py
|
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)
|
2 주 전 |
jais.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
jamba.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
llama.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
llama_embedding.py
|
9022c6d869
remove progress_bar imports
|
2 달 전 |
llava.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
llava_next.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
mamba.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
mamba_cache.py
|
bf88c8567e
feat: mamba model support (#674)
|
4 달 전 |
medusa.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
minicpm.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
minicpmv.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
mixtral.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
mixtral_quant.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
mlp_speculator.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
mpt.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
na_vit.py
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
2 주 전 |
nemotron.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
olmo.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
olmoe.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
opt.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
orion.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
paligemma.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
persimmon.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
phi.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
phi3_small.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
phi3v.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
phimoe.py
|
201db10f02
models: add support for Phi3 MoE
|
2 주 전 |
qwen.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
qwen2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
qwen2_moe.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
siglip.py
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 주 전 |
solar.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
stablelm.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
starcoder2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
ultravox.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |
utils.py
|
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)
|
2 주 전 |
xverse.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 주 전 |