| .. |
|
guided_decoding
|
313e198557
api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993)
|
il y a 2 semaines |
|
layers
|
7ca63930c8
support deepseek_v3 model
|
il y a 2 semaines |
|
model_loader
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
il y a 2 semaines |
|
models
|
7ca63930c8
support deepseek_v3 model
|
il y a 2 semaines |
|
__init__.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
il y a 3 semaines |
|
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
il y a 4 mois |
|
parameter.py
|
cec4da1dab
quants: support w8a8 fp8 block-wise quantization from DS3
|
il y a 2 semaines |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 4 mois |
|
sampling_metadata.py
|
f0cc35befe
sampler: pad dry sequence breakers tensor (#875)
|
il y a 1 mois |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
il y a 8 mois |
AlpinDale
7ca63930c8
support deepseek_v3 model