.. |
__init__.py
|
132aa2abe4
spec decode: add support for EAGLE (#899)
|
vor 2 Monaten |
arctic.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
baichuan.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
bart.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
blip.py
|
653d1a08d4
feat: add support for audio models (#891)
|
vor 2 Monaten |
blip2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
bloom.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
chameleon.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
chatglm.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
clip.py
|
03bd85c950
chore: multi-image support for llava-next (#935)
|
vor 2 Monaten |
commandr.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
dbrx.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
decilm.py
|
9022c6d869
remove progress_bar imports
|
vor 4 Monaten |
deepseek.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
deepseek_v2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
eagle.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
exaone.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
falcon.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
fuyu.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
gemma.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
gemma2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
gpt2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
gpt_bigcode.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
gpt_j.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
gpt_neox.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
idefics2_vision_model.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 6 Monaten |
interfaces.py
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
vor 6 Monaten |
intern_vit.py
|
9022c6d869
remove progress_bar imports
|
vor 4 Monaten |
internlm2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
internvl.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
jais.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
jamba.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
llama.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
llama_embedding.py
|
9022c6d869
remove progress_bar imports
|
vor 4 Monaten |
llava.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
llava_next.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
mamba.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
mamba_cache.py
|
bf88c8567e
feat: mamba model support (#674)
|
vor 6 Monaten |
medusa.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
minicpm.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
minicpmv.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
mixtral.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
mixtral_quant.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
mlp_speculator.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
mpt.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
na_vit.py
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
vor 2 Monaten |
nemotron.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
olmo.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
olmoe.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
opt.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
orion.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
paligemma.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
persimmon.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
phi.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
phi3_small.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
phi3v.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
qwen.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
qwen2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
qwen2_moe.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
siglip.py
|
03bd85c950
chore: multi-image support for llava-next (#935)
|
vor 2 Monaten |
solar.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
stablelm.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
starcoder2.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
ultravox.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
utils.py
|
2aabf8fcf7
vlm: fix errors on ragged NestedTensors (#953)
|
vor 2 Monaten |
xverse.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |