2 Commits

Author	SHA1	Message	Date
drslark	8fb0ef5ffa	[main][BugFix] Fixed an accuracy bug of Qwen3-next-MTP when batched inferring (#4932) ... ### What this PR does / why we need it? Fixes an accuracy bug of Qwen3-next-MTP when batched inferring. It is descibed in https://github.com/vllm-project/vllm-ascend/issues/4930. - vLLM version: v0.12.0 - vLLM main: ad32e3e19c Signed-off-by: drslark <slarksblood@qq.com>	2025-12-15 13:22:30 +08:00
drslark	0fb1dc43a1	[BugFix][main] Adapted Qwen3-Next-MTP to chunked prefill (#4770) ... ### What this PR does / why we need it? The pad `-1` modification is from https://github.com/vllm-project/vllm/pull/25743. It still has bugs for batched chunked prefill. - vLLM version: v0.12.0 - vLLM main: ad32e3e19c Signed-off-by: drslark <slarksblood@qq.com> Co-authored-by: Mengqing Cao <cmq0113@163.com>	2025-12-10 22:54:24 +08:00