vLLM 0.11.0 didn't bring PR (https://github.com/vllm-project/vllm/pull/25805) thus missing the prefix of mtp's SharedHead. This PR fixes this bug with a patch to vllm's deepseek_mtp. --------- Signed-off-by: whx-sjtu <2952154980@qq.com>
vLLM 0.11.0 didn't bring PR (https://github.com/vllm-project/vllm/pull/25805) thus missing the prefix of mtp's SharedHead. This PR fixes this bug with a patch to vllm's deepseek_mtp. --------- Signed-off-by: whx-sjtu <2952154980@qq.com>