biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] V1 Enablement Oracle (#13726)

Browse Source 
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw
2025-03-15 01:02:20 -04:00
committed by GitHub
parent 8c0d15d5c5
commit d4d93db2c5
96 changed files with 1537 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/lora/test_llama_tp.py
View File

@@ -80,6 +80,8 @@ def v1(run_with_both_engines_lora):
pass
# V1 Test: Failing due to numerics on V1.
@pytest.mark.skip_v1
@fork_new_process_for_each_test
def test_llama_lora(sql_lora_files):
@@ -123,6 +125,8 @@ def test_llama_lora_warmup(sql_lora_files):
"less when using lora than when not using lora")
# V1 Test: Failing due to numerics on V1.
@pytest.mark.skip_v1
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
def test_llama_lora_tp4(sql_lora_files):