Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4 (#11866)
This commit is contained in:
@@ -19,6 +19,9 @@ suites = {
|
||||
TestFile("hicache/test_hicache_eagle.py", 150),
|
||||
TestFile("hicache/test_hicache_mla.py", 127),
|
||||
TestFile("hicache/test_hicache_storage.py", 127),
|
||||
TestFile("layers/attention/mamba/test_causal_conv1d.py", 25),
|
||||
TestFile("layers/attention/mamba/test_mamba_ssm.py", 50),
|
||||
TestFile("layers/attention/mamba/test_mamba_ssm_ssd.py", 70),
|
||||
TestFile("lora/test_lora.py", 200),
|
||||
TestFile("lora/test_lora_eviction.py", 200),
|
||||
TestFile("lora/test_lora_eviction_policy.py", 200),
|
||||
@@ -34,7 +37,7 @@ suites = {
|
||||
TestFile("models/test_embedding_models.py", 73),
|
||||
TestFile("models/test_encoder_embedding_models.py", 460),
|
||||
TestFile("models/test_generation_models.py", 103),
|
||||
TestFile("models/test_nvidia_nemotron_nano_v2.py", 180),
|
||||
TestFile("models/test_nvidia_nemotron_nano_v2.py", 300),
|
||||
TestFile("models/test_qwen_models.py", 82),
|
||||
TestFile("batch_invariant/test_batch_invariant_ops.py", 10),
|
||||
TestFile("models/test_reward_models.py", 132),
|
||||
@@ -143,7 +146,7 @@ suites = {
|
||||
TestFile("hicache/test_hicache_storage_3fs_backend.py", 200),
|
||||
TestFile("hicache/test_hicache_storage_file_backend.py", 200),
|
||||
TestFile("hicache/test_hicache_storage_mooncake_backend.py", 400),
|
||||
TestFile("layers/attention/mamba/test_mamba2_mixer.py", 110),
|
||||
TestFile("layers/attention/mamba/test_mamba2_mixer.py", 50),
|
||||
TestFile("lora/test_lora_tp.py", 116),
|
||||
TestFile("models/test_glm4_moe_models.py", 100),
|
||||
TestFile("rl/test_update_weights_from_distributed.py", 103),
|
||||
|
||||
Reference in New Issue
Block a user