fix: Handles input_embeds in GenerateReqInput when n>1 (#7830)

Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
This commit is contained in:
Xinyuan Tong
2025-07-08 14:00:42 -07:00
committed by GitHub
parent 43e20c0647
commit 136c6e0431
3 changed files with 75 additions and 1 deletions

View File

@@ -67,6 +67,7 @@ suites = {
TestFile("test_hidden_states.py", 55),
TestFile("test_int8_kernel.py", 8),
TestFile("test_input_embeddings.py", 38),
TestFile("test_io_struct.py", 8),
TestFile("test_jinja_template_utils.py", 1),
TestFile("test_metrics.py", 32),
TestFile("test_mla.py", 167),