.. |
async_engine
|
9082ac7b7a
add async engine test units
|
vor 8 Monaten |
basic_correctness
|
3a206f9e11
add chunked prefill correctness test
|
vor 8 Monaten |
benchmarks
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
vor 9 Monaten |
distributed
|
9e1cea354c
add distributed system tests
|
vor 8 Monaten |
endpoints
|
e28c8496b2
endpoint tests
|
vor 8 Monaten |
engine
|
ce10891496
add more engine-related tests:
|
vor 8 Monaten |
fp8_kv
|
2172a9c374
add fp8_e4m3fn scales for llama2 7b and 70b
|
vor 8 Monaten |
kernels
|
e177788401
add moe tests
|
vor 8 Monaten |
models
|
e1f3fd1e02
fix: test units (#201)
|
vor 1 Jahr |
processing
|
54ed7adef3
add core processor tests
|
vor 8 Monaten |
prompts
|
e1f3fd1e02
fix: test units (#201)
|
vor 1 Jahr |
samplers
|
4d04ade9ef
feat: fine-grained seeds (#279)
|
vor 10 Monaten |
worker
|
e1f3fd1e02
fix: test units (#201)
|
vor 1 Jahr |
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
vor 1 Jahr |
conftest.py
|
54ed7adef3
add core processor tests
|
vor 8 Monaten |
test_regression.py
|
e1f3fd1e02
fix: test units (#201)
|
vor 1 Jahr |