frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI Failure] Fix tests with missing TinyLlama-1.1B-Chat-v1.0-FP8-e2e (#26816)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-10-14 14:38:59 -04:00
committed by GitHub
parent aba48f7db1
commit c3a722fcb2
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/compile/test_async_tp.py
View File

@ -332,7 +332,7 @@ def async_tp_pass_on_test_model(
# this is a fake model name to construct the model config
# in the vllm_config, it's not really used.
model_name = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-e2e"
model_name = "RedHatAI/Llama-3.2-1B-Instruct-FP8"
vllm_config.model_config = ModelConfig(
model=model_name, trust_remote_code=True, dtype=dtype, seed=42
)

2
tests/compile/test_fusion_all_reduce.py
View File

@ -229,7 +229,7 @@ def all_reduce_fusion_pass_on_test_model(
# this is a fake model name to construct the model config
# in the vllm_config, it's not really used.
model_name = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-e2e"
model_name = "RedHatAI/Llama-3.2-1B-Instruct-FP8"
vllm_config.model_config = ModelConfig(
model=model_name, trust_remote_code=True, dtype=dtype, seed=42
)

2
tests/compile/test_sequence_parallelism.py
View File

@ -278,7 +278,7 @@ def sequence_parallelism_pass_on_test_model(
# this is a fake model name to construct the model config
# in the vllm_config, it's not really used.
model_name = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-e2e"
model_name = "RedHatAI/Llama-3.2-1B-Instruct-FP8"
vllm_config.model_config = ModelConfig(
model=model_name, trust_remote_code=True, dtype=dtype, seed=42
)