[Test] E2E Nemotron-3-Super tests (#36803)
Signed-off-by: Roi Koren <roik@nvidia.com>
This commit is contained in:
@@ -90,6 +90,7 @@ steps:
|
|||||||
commands:
|
commands:
|
||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor-dp-ep/config-b200.txt
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor-dp-ep/config-b200.txt
|
||||||
|
|
||||||
|
|
||||||
- label: GPQA Eval (GPT-OSS) (H100)
|
- label: GPQA Eval (GPT-OSS) (H100)
|
||||||
timeout_in_minutes: 120
|
timeout_in_minutes: 120
|
||||||
device: h100
|
device: h100
|
||||||
|
|||||||
@@ -0,0 +1,11 @@
|
|||||||
|
model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
|
||||||
|
accuracy_threshold: 0.93
|
||||||
|
num_questions: 1319
|
||||||
|
num_fewshot: 5
|
||||||
|
startup_max_wait_seconds: 1200
|
||||||
|
server_args: >-
|
||||||
|
--enforce-eager
|
||||||
|
--max-model-len 4096
|
||||||
|
--tensor-parallel-size 8
|
||||||
|
--enable-expert-parallel
|
||||||
|
--speculative-config '{"method":"mtp","num_speculative_tokens":5}'
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"
|
||||||
|
accuracy_threshold: 0.93
|
||||||
|
num_questions: 1319
|
||||||
|
num_fewshot: 5
|
||||||
|
startup_max_wait_seconds: 1200
|
||||||
|
server_args: >-
|
||||||
|
--enforce-eager
|
||||||
|
--max-model-len 4096
|
||||||
|
--tensor-parallel-size 8
|
||||||
|
--enable-expert-parallel
|
||||||
|
--speculative-config '{"method":"mtp","num_speculative_tokens":5}'
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"
|
||||||
|
accuracy_threshold: 0.93
|
||||||
|
num_questions: 1319
|
||||||
|
num_fewshot: 5
|
||||||
|
startup_max_wait_seconds: 1200
|
||||||
|
server_args: >-
|
||||||
|
--enforce-eager
|
||||||
|
--max-model-len 4096
|
||||||
|
--tensor-parallel-size 2
|
||||||
|
--enable-expert-parallel
|
||||||
|
--speculative-config '{"method":"mtp","num_speculative_tokens":5}'
|
||||||
@@ -5,3 +5,4 @@ DeepSeek-V2-Lite-Instruct-FP8.yaml
|
|||||||
Qwen3-30B-A3B-NVFP4.yaml
|
Qwen3-30B-A3B-NVFP4.yaml
|
||||||
Qwen3-Next-80B-A3B-NVFP4-EP2.yaml
|
Qwen3-Next-80B-A3B-NVFP4-EP2.yaml
|
||||||
Qwen3-Next-FP8-EP2.yaml
|
Qwen3-Next-FP8-EP2.yaml
|
||||||
|
Nemotron-3-Super-120B-A12B-NVFP4.yaml
|
||||||
|
|||||||
@@ -2,3 +2,5 @@ DeepSeek-R1-TP.yaml
|
|||||||
DeepSeek-R1-DP.yaml
|
DeepSeek-R1-DP.yaml
|
||||||
DeepSeek-V3.2-TP.yaml
|
DeepSeek-V3.2-TP.yaml
|
||||||
DeepSeek-V3.2-DP.yaml
|
DeepSeek-V3.2-DP.yaml
|
||||||
|
Nemotron-3-Super-120B-A12B-BF16.yaml
|
||||||
|
Nemotron-3-Super-120B-A12B-FP8.yaml
|
||||||
|
|||||||
Reference in New Issue
Block a user