| .. |
|
guided_decoding
|
313e198557
api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993)
|
2 weeks ago |
|
layers
|
9bdf8d5bfa
mamba: enable continuous batching for mamba kernels (#1055)
|
1 week ago |
|
model_loader
|
b3f9ab3b72
quant: add tensor parallel support for bitsandbytes (#1052)
|
1 week ago |
|
models
|
11f49b5341
fix: granite logit scale in logit computation (#1054)
|
1 week ago |
|
__init__.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 weeks ago |
|
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
3 months ago |
|
parameter.py
|
83af2524f3
quants: add GPTQ and FBGEMM to AphroditeParameters (#987)
|
2 weeks ago |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
sampling_metadata.py
|
4593a3b306
chore: remove dead code from triton sampling kernels (#1049)
|
1 week ago |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 months ago |
AlpinDale
9bdf8d5bfa
mamba: enable continuous batching for mamba kernels (#1055)