.. |
attention.py
|
e1f3fd1e02
fix: test units (#201)
|
1 jaar geleden |
backend_request_func.py
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
1 jaar geleden |
hashing.py
|
c6a501f682
add multiprocessing executor; make ray optional
|
7 maanden geleden |
latency.py
|
e1f3fd1e02
fix: test units (#201)
|
1 jaar geleden |
launch_tgi.sh
|
4d04ade9ef
feat: fine-grained seeds (#279)
|
1 jaar geleden |
moe_config.py
|
6d2f00d728
benchmark script for fp8 MoE
|
7 maanden geleden |
serving.py
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
1 jaar geleden |
throughput.py
|
033797fd55
refactor throughput benchmark script
|
7 maanden geleden |