- 08 Feb, 2026 1 commit
-
-
王敏 authored
-
- 07 Jan, 2026 1 commit
-
-
laibao authored
- repeat_counts/CPU 元数据为 numpy/array-like 时会在 repeat_interleave/.to() 崩溃 - 统一转换为 CPU torch.Tensor 后再扩展并拷到 GPU
-
- 04 Jan, 2026 1 commit
-
-
laibao authored
新增环境变量开关 VLLM_V1_FAST_TOKEN_ID_COPY(默认关闭)。开启后在 CachedRequestState 中缓存 prompt_token_ids 的 np.int32,并在 add_request 里用 np.copyto 写入 token_ids_cpu,避免长 prompt 场景反复 list->NumPy 转换开销(尤其是抢占/反复进出 batch 时)
-
- 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
-
- 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
-
- 06 Sep, 2025 1 commit
-
-
lizhigong authored
-
- 02 Jul, 2025 1 commit
-
-
afeldman-nm authored
Signed-off-by:
Nick Hill <nhill@redhat.com> Signed-off-by:
Andrew Feldman <afeldman@neuralmagic.com> Signed-off-by:
Andrew Feldman <afeldman@redhat.com> Co-authored-by:
Nick Hill <nhill@redhat.com>
-
- 23 Jun, 2025 1 commit
-
-
Isotr0py authored
Signed-off-by:Isotr0py <2037008807@qq.com>
-
- 19 Jun, 2025 1 commit
-
-
Maximilien de Bayser authored
Signed-off-by:
Max de Bayser <mbayser@br.ibm.com> Signed-off-by:
Max de Bayser <maxdebayser@gmail.com> Signed-off-by:
22quinn <33176974+22quinn@users.noreply.github.com> Co-authored-by:
22quinn <33176974+22quinn@users.noreply.github.com>
-
- 18 Jun, 2025 1 commit
-
-
afeldman-nm authored
Signed-off-by:Andrew Feldman <afeldman@redhat.com>
-
- 10 Jun, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
- 03 Jun, 2025 2 commits
-
-
Chen Zhang authored
Signed-off-by:Chen Zhang <zhangch99@outlook.com>
-
Simon Mo authored
Signed-off-by:simon-mo <simon.mo@hey.com>
-
- 23 May, 2025 1 commit
-
-
Chen Zhang authored
Signed-off-by:Chen Zhang <zhangch99@outlook.com>
-
- 21 May, 2025 1 commit
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
- 15 May, 2025 1 commit
-
-
Chen Zhang authored
Signed-off-by:Chen Zhang <zhangch99@outlook.com>
-
- 10 May, 2025 1 commit
-
-
Chen Zhang authored
Signed-off-by:Chen Zhang <zhangch99@outlook.com>
-
- 26 Apr, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
- 01 Apr, 2025 1 commit
-
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
- 28 Mar, 2025 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 24 Mar, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
- 16 Mar, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
- 08 Mar, 2025 1 commit
-
-
22quinn authored
Signed-off-by:
22quinn <33176974+22quinn@users.noreply.github.com> Co-authored-by:
Nick Hill <nhill@redhat.com>
-
- 06 Mar, 2025 1 commit
-
-
Lucas Wilkinson authored
Signed-off-by:Lucas Wilkinson <lwilkins@redhat.com>
-
- 05 Mar, 2025 4 commits
-
-
Nick Hill authored
Signed-off-by:
Nick Hill <nhill@redhat.com> Co-authored-by:
Ye Cao <caoye.cao@alibaba-inc.com>
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
Robert Shaw authored
Signed-off-by:rshaw@neuralmagic.com <rshaw@neuralmagic.com>
-
Lu Fang authored
Signed-off-by:Lu Fang <lufang@fb.com>
-
- 03 Mar, 2025 1 commit
-
-
Harry Mellor authored
-
- 28 Feb, 2025 1 commit
-
-
Chen Zhang authored
Signed-off-by:Chen Zhang <zhangch99@outlook.com>
-
- 27 Feb, 2025 1 commit
-
-
Yang Chen authored
Signed-off-by:Yang Chen <yangche@fb.com>
-
- 26 Feb, 2025 1 commit
-
-
Lily Liu authored
-
- 22 Feb, 2025 1 commit
-
-
Lu Fang authored
Signed-off-by:Lu Fang <lufang@fb.com>
-
- 21 Feb, 2025 1 commit
-
-
Nick Hill authored
-
- 18 Feb, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
- 17 Feb, 2025 1 commit
-
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
- 16 Feb, 2025 1 commit
-
-
Lily Liu authored
Signed-off-by:LiuXiaoxuanPKU <lilyliupku@gmail.com>
-
- 14 Feb, 2025 1 commit
-
-
Aoyu authored
Signed-off-by:
Aoyu <aoyuzhan@amazon.com> Co-authored-by:
Aoyu <aoyuzhan@amazon.com>
-