- 10 Feb, 2026 1 commit
-
-
hhzhang16 authored
Signed-off-by:Hannah Zhang <hannahz@nvidia.com>
-
- 09 Feb, 2026 1 commit
-
-
MatejKosec authored
Wrap wait_for_deployment_ready() in try/except TimeoutError for both prefill and decode profiling sweeps On timeout: log error, record via add_profiling_error(), clean up the timed-out deployment, and continue to the next parallelization mapping Previously, a single deployment timeout would crash the entire profiler job
-
- 06 Feb, 2026 3 commits
-
-
Yan Ru Pei authored
Signed-off-by:PeaBrane <yanrpei@gmail.com>
-
dagil-nvidia authored
Signed-off-by:
Dan Gil <dagil@nvidia.com> Co-authored-by:
Cursor <cursoragent@cursor.com>
-
akshatha-k authored
Signed-off-by:
akshatha-k <akshutk@gmail.com> Signed-off-by:
-
- 05 Feb, 2026 3 commits
-
-
Yan Ru Pei authored
Signed-off-by: -
Yan Ru Pei authored
Signed-off-by: -
hhzhang16 authored
feat: remove default model name in Profiler; validate for one of served model name and model path in Profiler (#5950) Signed-off-by:
-
- 04 Feb, 2026 2 commits
-
-
Yan Ru Pei authored
Signed-off-by: -
hhzhang16 authored
Signed-off-by:
-
- 03 Feb, 2026 2 commits
-
-
Yan Ru Pei authored
Signed-off-by: -
hhzhang16 authored
Signed-off-by:
-
- 29 Jan, 2026 1 commit
-
-
Tanmay Verma authored
Co-authored-by:Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
-
- 28 Jan, 2026 1 commit
-
-
GuanLuo authored
Signed-off-by:Guan Luo <41310872+GuanLuo@users.noreply.github.com>
-
- 27 Jan, 2026 2 commits
-
-
Yan Ru Pei authored
Signed-off-by: -
Dmitry Tokarev authored
Signed-off-by:Dmitry Tokarev <dtokarev@nvidia.com>
-
- 26 Jan, 2026 1 commit
-
-
Jason Zhou authored
-
- 23 Jan, 2026 1 commit
-
-
jthomson04 authored
Signed-off-by:jthomson04 <jwillthomson19@gmail.com>
-
- 21 Jan, 2026 1 commit
-
-
Hongkuan Zhou authored
Signed-off-by:hongkuanz <hongkuanz@nvidia.com>
-
- 18 Jan, 2026 1 commit
-
-
Yan Ru Pei authored
Signed-off-by:
-
- 16 Jan, 2026 3 commits
-
-
hhzhang16 authored
Signed-off-by: -
Yan Ru Pei authored
Signed-off-by: -
Yan Ru Pei authored
Signed-off-by:
-
- 15 Jan, 2026 1 commit
-
-
dagil-nvidia authored
Signed-off-by:
-
- 14 Jan, 2026 1 commit
-
-
MatejKosec authored
Extends the MOE planner profiler to support TEP (tensor expert parallel) and DEP (data expert parallel) configs with the vllm backend
-
- 13 Jan, 2026 1 commit
-
-
Elias Bermudez authored
Signed-off-by:
Anant Sharma <anants@nvidia.com> Co-authored-by:
-
- 12 Jan, 2026 2 commits
-
-
hhzhang16 authored
Signed-off-by: -
Tanmay Verma authored
-
- 09 Jan, 2026 1 commit
-
-
hhzhang16 authored
Signed-off-by:
-
- 08 Jan, 2026 1 commit
-
-
ishandhanani authored
-
- 07 Jan, 2026 1 commit
-
-
Ryan McCormick authored
-
- 06 Jan, 2026 2 commits
-
-
Hongkuan Zhou authored
Signed-off-by: -
Alec authored
Signed-off-by:alec-flowers <aflowers@nvidia.com>
-
- 05 Jan, 2026 1 commit
-
-
Hongkuan Zhou authored
Signed-off-by:
-
- 02 Jan, 2026 2 commits
-
-
Tushar Sharma authored
Signed-off-by:Tushar Sharma <tusharma@nvidia.com>
-
Nate Mailhot authored
Signed-off-by:Nate Mailhot <nmailhot@nvidia.com>
-
- 01 Jan, 2026 1 commit
-
-
Hongkuan Zhou authored
Signed-off-by:
-
- 31 Dec, 2025 2 commits
-
-
Yan Ru Pei authored
Signed-off-by:
Ishan Dhanani <ishandhanani@gmail.com> Co-authored-by:
Sean SH Choi <sechoi@nvidia.com> Co-authored-by:
ishandhanani <82981111+ishandhanani@users.noreply.github.com>
-
Hongkuan Zhou authored
Signed-off-by:
-
- 23 Dec, 2025 1 commit
-
-
Thomas Montfort authored
-
