| .. |
|
guided_decoding
|
e1eb7fbedc
fix: SentencePieceTokenizer error when using mistral tokenizer mode (#943)
|
2 months ago |
|
layers
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 months ago |
|
model_loader
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 months ago |
|
models
|
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)
|
2 months ago |
|
__init__.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
2 months ago |
|
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
6 months ago |
|
parameter.py
|
afc9a28aa0
chore: add AphroditeParameter support for FP8 quant (#902)
|
2 months ago |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 months ago |
|
sampling_metadata.py
|
f0cc35befe
sampler: pad dry sequence breakers tensor (#875)
|
3 months ago |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 months ago |
AlpinDale
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)