mindef-overdracht/llm-throughput-tests-mindef-metadateren/results/results_QuantTrio_Qwen3_5-35B-A3B-AWQ/config_used.yaml
2026-06-02 11:46:20 +02:00

26 lines
491 B
YAML

endpoint:
url: https://0e799c11-4b01-4acd-a91c-5e43deaae940.services.external.0a71m37v.ubiops.io/v1
api_key: <REDACTED>
model_name: QuantTrio/Qwen3.5-35B-A3B-AWQ
benchmark:
input_tokens:
- 1000
- 10000
- 50000
batch_sizes:
- 1
- 8
- 32
- 64
num_batches: 2
output_tokens: 512
dataset: test_conversations.json
text: null
runtime:
request_timeout: 300
delay_between_runs: 5
log_io: true
wait_for_ready: true
max_init_retries: 10
init_retry_delay: 30