Input_embeds support (#2052)

2024-11-25 19:35:04 -05:00
parent 1f76fc6e3f
commit 1aea19f64b
9 changed files with 204 additions and 15 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -14,6 +14,7 @@ suites = {
        "test_double_sparsity.py",
        "test_embedding_openai_server.py",
        "test_eval_accuracy_mini.py",
+        "test_input_embeddings.py",
        "test_json_constrained.py",
        "test_large_max_new_tokens.py",
        "test_metrics.py",