| .. |
|
fused_moe
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
mamba
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
ops
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
há 1 ano atrás |
|
activation.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
layernorm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
linear.py
|
df208ab4e9
fix: fp8 checkpoints with fused linear modules (#677)
|
há 4 meses atrás |
|
logits_processor.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
há 4 meses atrás |
|
pooler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
rejection_sampler.py
|
e3a53712f2
fix: mlpspeculator with padded vocab (#669)
|
há 4 meses atrás |
|
rotary_embedding.py
|
5d37ec1016
suppress tpu import warning (#696)
|
há 4 meses atrás |
|
sampler.py
|
1394008421
chore: decouple `should_modify_greedy_probs_inplace (#671)
|
há 4 meses atrás |
|
spec_decode_base_sampler.py
|
09b82f9963
feat: Add support for GPU device selection in SpecDecodeBaseSampler (#629)
|
há 5 meses atrás |
|
typical_acceptance_sampler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
|
vocab_parallel_embedding.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
AlpinDale
5d37ec1016
suppress tpu import warning (#696)