- 24 Dec, 2025 1 commit
-
-
laibao authored
新增环境变量 VLLM_V1_USE_REDUCED_TOPK_TOPP_SAMPLER 用于开关控制 扩展 SamplingMetadata,增加 max_top_k 与 has_any_no_top_k 在 InputBatch 侧计算 top-k 的主机端汇总信息,避免 device 同步 更新 Sampler/TopKTopPSampler 传递并使用新参数以启用优化采样
-
- 09 Dec, 2025 1 commit
-
-
王敏 authored
-
- 08 Dec, 2025 2 commits
- 05 Dec, 2025 1 commit
-
-
laibao authored
- 在 InputBatch.refresh_metadata 中为展开后的采样元数据引入 repeat_count 记录重复次数 - 完善元数据刷新逻辑以适配 reject-sampling 优化路径 - 更新 GPUModelRunnerBase,在 batch 处理阶段正确消费新的采样元数据与重复计数
-
- 27 Nov, 2025 1 commit
-
-
王敏 authored
-
- 26 Nov, 2025 2 commits
- 21 Nov, 2025 1 commit
-
-
jujl1 authored
-
- 17 Oct, 2025 1 commit
-
-
zhuwenwen authored
-
- 13 Oct, 2025 1 commit
-
-
王敏 authored
-
- 11 Oct, 2025 2 commits
- 10 Oct, 2025 3 commits
- 09 Oct, 2025 1 commit
-
-
zhuwenwen authored
This reverts merge request !219
-
- 26 Sep, 2025 1 commit
-
-
lizhigong authored
-
- 25 Sep, 2025 1 commit
-
-
yangshj1 authored
-
- 24 Sep, 2025 2 commits
- 16 Sep, 2025 1 commit
-
-
yangshj1 authored
-
- 06 Sep, 2025 1 commit
-
-
lizhigong authored
-
- 04 Sep, 2025 2 commits
- 03 Sep, 2025 1 commit
-
-
lizhigong authored
-
- 01 Sep, 2025 1 commit
-
-
王敏 authored
-
- 27 Aug, 2025 1 commit
-
-
lizhigong authored
-
- 19 Aug, 2025 1 commit
-
-
zhuwenwen authored
-
- 18 Aug, 2025 1 commit
-
-
王敏 authored
-
- 16 Aug, 2025 1 commit
-
-
lizhigong authored
-
- 15 Aug, 2025 1 commit
-
-
lizhigong authored
-
- 14 Aug, 2025 1 commit
-
-
zhuwenwen authored
-
- 13 Aug, 2025 2 commits
- 11 Aug, 2025 1 commit
-
-
lizhigong authored
-
- 08 Aug, 2025 1 commit
-
-
zhuwenwen authored
-
- 07 Aug, 2025 2 commits
- 06 Aug, 2025 1 commit
-
-
王敏 authored
-