| .. |
|
benchmarks
|
ee5964465d
chore: max_num_seqs in throughput benchmark (#770)
|
3 months ago |
|
distributed
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
endpoints
|
8a71788372
Add OLMoE (#772)
|
2 months ago |
|
engine
|
8a71788372
Add OLMoE (#772)
|
2 months ago |
|
kernels
|
e1f3fd1e02
fix: test units (#201)
|
1 year ago |
|
models
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
prompts
|
e1f3fd1e02
fix: test units (#201)
|
1 year ago |
|
samplers
|
8a71788372
Add OLMoE (#772)
|
2 months ago |
|
tokenization
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
worker
|
8a71788372
Add OLMoE (#772)
|
2 months ago |
|
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
1 year ago |
|
conftest.py
|
72229a94da
feat: better marlin kernels (#285)
|
10 months ago |
|
test_regression.py
|
e1f3fd1e02
fix: test units (#201)
|
1 year ago |
Fizz~
8a71788372
Add OLMoE (#772)