Skip to content

[#8542][feat] AutoDeploy: add Llama-3.1-8B FP8 perf-sanity test on H100 #14039

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

Open
MrGeva wants to merge 1 commit into
base: main
Choose a base branch
from
+24 −0
Open

[#8542][feat] AutoDeploy: add Llama-3.1-8B FP8 perf-sanity test on H100 #14039

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions tests/integration/defs/perf/test_perf_sanity.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@
"llama_v3.3_70b_instruct_fp4": "llama-3.3-models/Llama-3.3-70B-Instruct-FP4",
"deepseek_v3_lite_fp8": "DeepSeek-V3-Lite/fp8",
"llama_v3.1_8b_instruct": "llama-3.1-model/Llama-3.1-8B-Instruct",
"llama_v3.1_8b_instruct_fp8": "llama-3.1-model/Llama-3.1-8B-Instruct-FP8",
"glm_5_nvfp4": "GLM-5-NVFP4",
}

Expand Down
2 changes: 2 additions & 0 deletions tests/integration/test_lists/test-db/l0_h100.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -523,3 +523,5 @@ l0_h100:
- examples/test_ad_speculative_decoding.py::test_eagle_wrapper_forward[2]
- examples/test_ad_speculative_decoding.py::test_nemotron_mtp_model_with_weights
- examples/test_ad_guided_decoding.py::test_autodeploy_guided_decoding_main_json
# ------------- AutoDeploy Perf Sanity ---------------
- perf/test_perf_sanity.py::test_e2e[aggr_upload-llama3_1_8b_fp8_ad_hopper-llama3_1_8b_ad_ws1_1k1k] TIMEOUT (120)
21 changes: 21 additions & 0 deletions tests/scripts/perf-sanity/aggregated/llama3_1_8b_fp8_ad_hopper.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
metadata:
model_name: llama_v3.1_8b_instruct_fp8
supported_gpus:
- H100
- H200
hardware:
gpus_per_node: 1
server_configs:
# 1k1k config - AutoDeploy backend, 1 GPU (Llama-3.1-8B FP8 on Hopper)
- name: "llama3_1_8b_ad_ws1_1k1k"
model_name: "llama_v3.1_8b_instruct_fp8"
backend: "_autodeploy"
extra_llm_api_config_path: "examples/auto_deploy/model_registry/configs/llama3_1_8b.yaml"
world_size: 1
client_configs:
- name: "con64_iter10_1k1k"
concurrency: 64
iterations: 10
isl: 1024
osl: 1024
backend: "openai"
Loading