.. |
guided_decoding
|
313e198557
api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993)
|
2 mēneši atpakaļ |
layers
|
2261a0e8dd
cpu: fix issue with sampling kernels (#1016)
|
2 mēneši atpakaļ |
model_loader
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
2 mēneši atpakaļ |
models
|
a113309876
kernel: add meta functions for ops to prevent graph breaks (#1019)
|
2 mēneši atpakaļ |
__init__.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
2 mēneši atpakaļ |
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
6 mēneši atpakaļ |
parameter.py
|
83af2524f3
quants: add GPTQ and FBGEMM to AphroditeParameters (#987)
|
2 mēneši atpakaļ |
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mēneši atpakaļ |
sampling_metadata.py
|
f0cc35befe
sampler: pad dry sequence breakers tensor (#875)
|
3 mēneši atpakaļ |
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 mēneši atpakaļ |