| .. |
|
fused_moe
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
3 달 전 |
|
mamba
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
|
ops
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 년 전 |
|
activation.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
|
layernorm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
|
linear.py
|
edec2e9a9e
feat: migrate awq and awq_marlin to AphroditeParameter (#702)
|
4 달 전 |
|
logits_processor.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 달 전 |
|
pooler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
|
rejection_sampler.py
|
e3a53712f2
fix: mlpspeculator with padded vocab (#669)
|
4 달 전 |
|
rotary_embedding.py
|
4434c4db84
chore: refactor llama3 rope (#748)
|
3 달 전 |
|
sampler.py
|
198029295c
fix: empty sampler output when temperature is too low (#709)
|
4 달 전 |
|
spec_decode_base_sampler.py
|
09b82f9963
feat: Add support for GPU device selection in SpecDecodeBaseSampler (#629)
|
4 달 전 |
|
typical_acceptance_sampler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
|
vocab_parallel_embedding.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 달 전 |
AlpinDale
4434c4db84
chore: refactor llama3 rope (#748)