[Bugfix] fix bug for mtp (#6514)
### What this PR does / why we need it? fix(mtp): resolve MTP core bugs and enhance eager mode test cases 1. Resolved critical issues in eager mode MTP core execution logic; 2. Fixed functional bugs in the _update_states_after_model_execute function; 3. Updated and released test_mtp_qwen3_next.py to validate eager mode acceptance rate. ### Does this PR introduce _any_ user-facing change? None ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0 Signed-off-by: Bowen-Leee <caoshankuangren@gmail.com>
This commit is contained in:
@@ -54,7 +54,6 @@ def test_qwen3_next_mtp_acceptance_tp4(model_name):
|
||||
distributed_executor_backend="mp",
|
||||
disable_log_stats=False,
|
||||
speculative_config={
|
||||
"cudagraph_mode": "FULL_DECODE_ONLY",
|
||||
"method": "qwen3_next_mtp",
|
||||
"num_speculative_tokens": 3,
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user