Skip to content

Add google/gemma-3n-E2B-it #89

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Add google/gemma-3n-E2B-it #89

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3c9de9f
[no ci] Add add-gemma-3n-E2B-it
huydhn Oct 3, 2025
44ad43f
[no ci] Run with VLLM_USE_STANDALONE_COMPILE set
huydhn Oct 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions .github/workflows/vllm-benchmark.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,6 +263,8 @@ jobs:
# vLLM-related environment variables
ENGINE_VERSION: v1
SAVE_TO_PYTORCH_BENCHMARK_FORMAT: 1
# Test
VLLM_USE_STANDALONE_COMPILE: 1
run: |
set -eux

Expand All @@ -282,6 +284,7 @@ jobs:
-e HF_TOKEN \
-e ENGINE_VERSION \
-e SAVE_TO_PYTORCH_BENCHMARK_FORMAT \
-e VLLM_USE_STANDALONE_COMPILE \
-e ON_CPU="${ON_CPU}" \
--ipc=host \
--tty \
Expand Down
11 changes: 11 additions & 0 deletions vllm-benchmarks/benchmarks/cuda/latency-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,17 @@
"max_model_len": 8192
}
},
{
"test_name": "latency_gemma_3n_e2b_tp1",
"parameters": {
"model": "google/gemma-3n-E2B-it",
"tensor_parallel_size": 1,
"load_format": "dummy",
"num_iters_warmup": 5,
"num_iters": 15,
"max_model_len": 8192
}
},
{
"test_name": "latency_qwen3_30b_a3b_tp8",
"parameters": {
Expand Down
21 changes: 21 additions & 0 deletions vllm-benchmarks/benchmarks/cuda/serving-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -532,5 +532,26 @@
"random_input_len": 5250,
"random_output_len": 8250
}
},
{
"test_name": "serving_gemma_3n_e2b_tp1_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "google/gemma-3n-E2B-it",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "google/gemma-3n-E2B-it",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
}
]
12 changes: 12 additions & 0 deletions vllm-benchmarks/benchmarks/cuda/throughput-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,18 @@
"max_model_len": 8192
}
},
{
"test_name": "throughput_gemma_3n-e2b_tp1",
"parameters": {
"model": "google/gemma-3n-E2B-it",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm",
"max_model_len": 8192
}
},
{
"test_name": "throughput_qwen3_30b_a3b_tp8",
"parameters": {
Expand Down
Loading