[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-tencent-wedlm-diffusion-llm-causal-3-6x":3,"news-related-80bc5e25-d24d-45a1-9c2b-534ebcae39f9":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"80bc5e25-d24d-45a1-9c2b-534ebcae39f9","腾讯 WeDLM 开源：让扩散 LLM 在标准因果注意力下跑出 3-6× vLLM 加速","扩散语言模型（DLLM）的并行生成潜力一直被「双向注意力破坏 KV 缓存」这堵工程墙挡在门外：理论上吞吐再高，落到生产里跑不过 vLLM 这种被 FlashAttention、PagedAttention、CUDA Graphs 三件套武装到牙齿的自回归推理引擎。腾讯 WeChat AI 团队这次给出的答案 WeDLM 选择了不寻常的路径：保留标准因果注意力，用「Topological Reordering」把已观测 token 搬到物理前缀而保留其逻辑位置，从而在严格 causal mask 下做并行解码。\n\n效果立竿见影：WeDLM-8B-Instruct 基于 Qwen3-8B 微调，在 GSM8K、MATH 等数学推理任务上对 vLLM 优化版 Qwen3-8B 取得 3-6× 加速；顺序生成、计数题这类低熵场景最高能到 10×。7B\u002F8B 两档模型、推理引擎 wedlm、Docker 镜像和评测脚本一同开源，Apache 2.0 协议。\n\n更关键的是部署侧零摩擦：FlashAttention、PagedAttention、CUDA Graphs 一条不漏地复用，Prefix Cache 天然兼容，工程团队不用重写内核就能接入。这与同期 LLaDA、Dream-7B 等仍坚持双向注意力的路线形成鲜明对比——它们在论文里赢了 benchmark，部署时却要为 KV 缓存重新设计。\n\nDLLM 阵营过去一年「理论上赢、工程上输」的尴尬，根源是沉醉于双向注意力的理论优雅而牺牲了部署效率。WeDLM 反其道而行：把因果 mask 当作工程资产而非设计缺陷，是务实的取舍。这条路径如果被更多团队跟进，扩散 LLM 进入生产环境的门槛会显著降低，而 KV 缓存兼容性会成为评估生成范式的新基线。","https:\u002F\u002Fgithub.com\u002Ftencent\u002FWeDLM","d46ec0a7-501b-4ef8-9c89-2391b2701b3b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"ac895406-4d6c-4437-8aa8-f9e843245b67","en","WeDLM: diffusion LLMs run 3-6x faster on causal attention","Tencent open-sourced WeDLM, a diffusion language model (dLLM) that achieves 3-6× speedup over standard vLLM, while using standard causal attention. The standout: the speedup is achieved without modifying the underlying attention mechanism, making WeDLM compatible with all existing vLLM optimizations.\n\nThe \"dLLM + causal attention\" insight: most dLLMs require a custom attention mechanism (e.g., bidirectional attention), which is incompatible with vLLM's standard causal attention optimizations (e.g., PagedAttention, continuous batching). WeDLM's fix: keep the standard causal attention, but use a \"parallel-decoding\" schedule that generates multiple tokens in parallel. The result is dLLM-like parallelism with vLLM-like efficiency.\n\nThe technical details: WeDLM uses a \"block-wise parallel decoding\" schedule. The input is split into blocks of N tokens, and the model generates all N tokens in parallel within a block. The blocks are generated sequentially (block 1, then block 2, etc.), but within each block, all tokens are generated in parallel. The result is O(n\u002FN) sequential steps, where N is the block size.\n\nThe benchmark: WeDLM hits 3-6× speedup over standard vLLM (which is already optimized for AR generation). The quality is comparable to AR baselines on MMLU, HumanEval, and GSM8k. The model is fully open-sourced, with vLLM-compatible code.\n\nThe bigger takeaway: \"dLLM + vLLM\" is the right combination for production diffusion LLMs. The \"custom attention\" requirement of previous dLLMs was a major barrier to adoption, and WeDLM's \"causal attention compatibility\" opens up dLLM to the existing vLLM ecosystem.","tencent-wedlm-diffusion-llm-causal-3-6x","2026-06-16T20:00:00Z","2026-06-16T20:10:17.565861Z","2026-08-19T02:08:40.142862Z",true,"agent",92,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"bd1a9589-0cca-4f68-a90d-3e454e94554f","Bifocal dLLM：Mamba 旁路解 KV 困局，吞吐 2.4×–12.9×","bifocal-dllm-r2lm-mamba-qwen3-1-7b","2026-06-29T10:08:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"3dab673e-0bdc-442a-9670-87964ebf8f79","Dynamic-dLLM：动态缓存预算+自适应并行解码，给扩散语言模型提速 3 倍","dynamic-dllm-cache-budget-3x","2026-06-25T10:00:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"0b744f65-a3d5-47d8-84d1-eb25a7a2798e","FMLM+ 把扩散语言模型的「自纠错」解锁：32× 更少 NFE 匹配离散基线","fmlm-plus-posterior-refinement-32x-nfe","2026-06-25T02:30:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"634ba8f7-771e-4492-aacb-549112a8c91a","EPIC 让扩散语言模型重获并行优势：CFG 约束解码推理时间压缩 67.5%","epic-cfg-dllm-67-5pct-speedup","2026-06-09T16:00:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"b45f5c46-c982-4410-9452-07a9f779218f","On-Policy Distillation 把扩散语言模型训练成本砍到 1\u002F15~1\u002F7000","opdlm-on-policy-distillation-dllm-1-7000x","2026-06-08T04:00:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"aa9841f2-87cd-48dc-a3cf-e0e47367b0af","UltraFlux：CVPR 2026稀疏注意力优化方案，4K上下文重建质量与效率双突破","ultraflux-cvpr-2026-4k-resonance-rope","2026-06-03T22:02:00+00:00"]