kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-05 02:31:33 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][chore] update config.yaml of slurm scripts to align with submit.py change (#10802)

Browse Source 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
This commit is contained in:
Zhenhuan Chen 2026-01-20 03:46:23 +08:00 committed by GitHub
parent ed95e70150
commit 066fa4cd93
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
examples/disaggregated/slurm/benchmark/config.yaml
View File

@ -49,9 +49,12 @@ profiling:
# Accuracy Configuration
accuracy:
enable_accuracy_test: false # Set to true to enable accuracy evaluation
model: "local-completions" # Model type for lm_eval
tasks: "gsm8k" # Evaluation tasks (comma-separated)
model_args_extra: "num_concurrent=512,max_retries=3,tokenized_requests=false,timeout=1200,max_gen_toks=256,max_length=4096" # Extra model arguments for lm_eval
tasks:
gsm8k:
model: "local-completions" # Model type for lm_eval
model_args_extra: "num_concurrent=512,max_retries=3,tokenized_requests=false,timeout=7200,max_gen_toks=16384"
extra_kwargs:
trust_remote_code: true
worker_config:
gen:

9
examples/wide_ep/slurm_scripts/config.yaml
View File

@ -47,9 +47,12 @@ profiling:
# Accuracy Configuration
accuracy:
enable_accuracy_test: false # Set to true to enable accuracy evaluation
model: "local-completions" # Model type for lm_eval
tasks: "gsm8k" # Evaluation tasks (comma-separated)
model_args_extra: "num_concurrent=512,max_retries=3,tokenized_requests=false,timeout=1200,max_gen_toks=256,max_length=4096" # Extra model arguments for lm_eval
tasks:
gsm8k:
model: "local-completions" # Model type for lm_eval
model_args_extra: "num_concurrent=512,max_retries=3,tokenized_requests=false,timeout=7200,max_gen_toks=16384"
extra_kwargs:
trust_remote_code: true
worker_config:
gen: