| .. |
|
guided_decoding
|
313e198557
api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993)
|
hai 1 mes |
|
layers
|
f20f5c3491
samplers: improved DRY performance (#1108)
|
hai 1 semana |
|
model_loader
|
b3f9ab3b72
quant: add tensor parallel support for bitsandbytes (#1052)
|
hai 1 mes |
|
models
|
fc5ef786b0
Merge branch 'main' into lm_head_lora
|
hai 6 días |
|
__init__.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hai 1 mes |
|
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
hai 4 meses |
|
parameter.py
|
83af2524f3
quants: add GPTQ and FBGEMM to AphroditeParameters (#987)
|
hai 1 mes |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 5 meses |
|
sampling_metadata.py
|
f20f5c3491
samplers: improved DRY performance (#1108)
|
hai 1 semana |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 8 meses |
AlpinDale
fc5ef786b0
Merge branch 'main' into lm_head_lora