- 21 Jan, 2026 2 commits
-
-
blarson-b10 authored
Signed-off-by:Brian Larson <brian.larson@baseten.co>
-
Janelle Cai authored
-
- 20 Jan, 2026 11 commits
-
-
ishandhanani authored
Co-authored-by:Claude Opus 4.5 <noreply@anthropic.com>
-
Schwinn Saereesitthipitak authored
-
ishandhanani authored
-
MatejKosec authored
This ensures that only new tokens are returned by sglang which avoids the overhead from creating copies of the entire token sequences per each iteration. These copies can become a bottleneck particularly for long sequence lengths and large concurrency counts. Signed-off-by:Matej Kosec <mkosec@nvidia.com>
-
Keiven C authored
Co-authored-by:Keiven Chang <keivenchang@users.noreply.github.com>
-
jthomson04 authored
Signed-off-by:jthomson04 <jwillthomson19@gmail.com>
-
Schwinn Saereesitthipitak authored
Signed-off-by:
Schwinn Saereesitthipitak <schwinns@nvidia.com> Co-authored-by:
Claude Opus 4.5 <noreply@anthropic.com>
-
Schwinn Saereesitthipitak authored
Signed-off-by:
Schwinn Saereesitthipitak <schwinns@nvidia.com> Co-authored-by:
Claude Opus 4.5 <noreply@anthropic.com>
-
Michael Feil authored
Signed-off-by:
Michael Feil <63565275+michaelfeil@users.noreply.github.com> Co-authored-by:
Anant Sharma <anants@nvidia.com>
-
Graham King authored
Signed-off-by:Graham King <grahamk@nvidia.com>
-
Schwinn Saereesitthipitak authored
Signed-off-by:
Schwinn Saereesitthipitak <schwinns@nvidia.com> Co-authored-by:
Claude Opus 4.5 <noreply@anthropic.com>
-
- 18 Jan, 2026 3 commits
-
-
Yan Ru Pei authored
Signed-off-by:PeaBrane <yanrpei@gmail.com>
-
blarson-b10 authored
Signed-off-by:Brian Larson <brian.larson@baseten.co>
-
Yan Ru Pei authored
Signed-off-by:PeaBrane <yanrpei@gmail.com>
-
- 17 Jan, 2026 1 commit
-
-
Pavithra Vijayakrishnan authored
Signed-off-by:pvijayakrish <pvijayakrish@nvidia.com>
-
- 16 Jan, 2026 13 commits
-
-
hhzhang16 authored
Signed-off-by:Hannah Zhang <hannahz@nvidia.com>
-
Neelay Shah authored
Co-authored-by:Claude Opus 4.5 <noreply@anthropic.com>
-
Neal Vaidya authored
Signed-off-by:Neal Vaidya <nealv@nvidia.com>
-
Ayush Agarwal authored
Signed-off-by:ayushag <ayushag@nvidia.com>
-
Anant Sharma authored
Signed-off-by:Anant Sharma <anants@nvidia.com>
-
Anant Sharma authored
Signed-off-by:Anant Sharma <anants@nvidia.com>
-
Dmitry Tokarev authored
Signed-off-by:
Dmitry Tokarev <dtokarev@nvidia.com> Signed-off-by:
Anant Sharma <anants@nvidia.com> Co-authored-by:
Anant Sharma <anants@nvidia.com>
-
Keiven C authored
Signed-off-by:
Keiven Chang <keivenchang@users.noreply.github.com> Co-authored-by:
Keiven Chang <keivenchang@users.noreply.github.com>
-
Graham King authored
Signed-off-by:Graham King <grahamk@nvidia.com>
-
KrishnanPrash authored
-
Yan Ru Pei authored
Signed-off-by:PeaBrane <yanrpei@gmail.com>
-
Yan Ru Pei authored
Signed-off-by:PeaBrane <yanrpei@gmail.com>
-
Pavithra Vijayakrishnan authored
Signed-off-by:
pvijayakrish <pvijayakrish@nvidia.com> Signed-off-by:
Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
-
- 15 Jan, 2026 8 commits
-
-
GuanLuo authored
Signed-off-by:Guan Luo <41310872+GuanLuo@users.noreply.github.com>
-
Biswa Panda authored
-
Neelay Shah authored
Co-authored-by:Claude Opus 4.5 <noreply@anthropic.com>
-
dagil-nvidia authored
Signed-off-by:Dan Gil <dagil@nvidia.com>
-
dagil-nvidia authored
Signed-off-by:Dan Gil <dagil@nvidia.com>
-
jh-nv authored
-
atchernych authored
Signed-off-by:Anna Tchernych <atchernych@nvidia.com>
-
Anish authored
Signed-off-by:
Dan Gil <dagil@nvidia.com> Co-authored-by:
Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by:
Dan Gil <dagil@nvidia.com>
-
- 14 Jan, 2026 2 commits
-
-
Ryan McCormick authored
Signed-off-by:Ryan McCormick <rmccormick@nvidia.com>
-
Harrison Saturley-Hall authored
Signed-off-by:Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
-