This website requires JavaScript.
Explore
Help
Register
Sign In
qqtang
/
sskj
Watch
1
Star
3
Fork
0
You've already forked sskj
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
sskj
/
experiments
/
pro6000
/
dsv4_pro6000_sglang_tp16
History
Zhiyi Hong
cd362c5ca0
fix: max_running_requests=256, cuda_graph_max_bs=256 to match max concurrency 128
2026-07-28 17:20:25 +08:00
..
config.env
fix: max_running_requests=256, cuda_graph_max_bs=256 to match max concurrency 128
2026-07-28 17:20:25 +08:00
run_batch.sh
add tp = 16 deepseek v4 pro sglang bench
2026-07-28 17:09:26 +08:00
start_and_bench.sh
add tp = 16 deepseek v4 pro sglang bench
2026-07-28 17:09:26 +08:00
start_sglang_multinode.sh
add tp = 16 deepseek v4 pro sglang bench
2026-07-28 17:09:26 +08:00
stop_sglang_multinode.sh
add tp = 16 deepseek v4 pro sglang bench
2026-07-28 17:09:26 +08:00