Skip to content

GitLab

"examples/avsr/data_prep/data/data_module.py" did not exist on "77cdd160f15f63f18c35e7f2d885dcc14e85a846"
Unverified Commit ac5b78ba authored by Yineng Zhang's avatar Yineng Zhang Committed by GitHub
Browse files

fix: update test config (#5392)

parent 38076dea
Hide whitespace changes
Inline Side-by-side
Showing with 7 additions and 7 deletions
test/srt/configs/llama_405b.yaml
View file @ ac5b78ba
tasks:
- name: sglang-8192-1024-concurrency1
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 1 --num-prompts 5 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 1 --num-prompts 5 --output-file llama_405b_results.jsonl
- name: sglang-8192-1024-concurrency2
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 2 --num-prompts 10 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 2 --num-prompts 10 --output-file llama_405b_results.jsonl
- name: sglang-8192-1024-concurrency4
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 4 --num-prompts 20 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 4 --num-prompts 20 --output-file llama_405b_results.jsonl
- name: sglang-8192-1024-concurrency8
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 8 --num-prompts 32 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 8 --num-prompts 32 --output-file llama_405b_results.jsonl
- name: sglang-8192-1024-concurrency16
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 16 --num-prompts 48 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 16 --num-prompts 48 --output-file llama_405b_results.jsonl
- name: sglang-8192-1024-concurrency24
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 24 --num-prompts 72 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 24 --num-prompts 72 --output-file llama_405b_results.jsonl
- name: sglang-8192-1024-concurrency32
server_cmd: python3 -m sglang.launch_server --model nvidia/Llama-3.1-405B-Instruct-FP8 --tp 8
client_cmd: python3 -m sglang.bench_serving --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 32 --num-prompts 96 --output-file llama_405b_results.jsonl
client_cmd: python3 -m sglang.bench_serving --dataset-name random --random-range-ratio 1 --random-input-len 8192 --random-output-len 1024 --max-concurrency 32 --num-prompts 96 --output-file llama_405b_results.jsonl
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment