[Deprecation] Remove prompt_token_ids arg fallback in LLM.generate and LLM.embed (#18800)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-22 10:56:57 +08:00
parent 19fe1a0510
commit 8896eb72eb
24 changed files with 116 additions and 467 deletions
--- a/tests/quantization/test_lm_head.py
+++ b/tests/quantization/test_lm_head.py
@@ -46,5 +46,5 @@ def test_lm_head(
        vllm_model.apply_model(check_model)

        print(
-            vllm_model.generate_greedy(prompts=["Hello my name is"],
+            vllm_model.generate_greedy(["Hello my name is"],
                                       max_tokens=10)[0][1])