MatejKosec
|
7cfd966e51
|
feat: SLA Planner configuration support for DEP and TEP VLLM (#4783)
Extends the MOE planner profiler to support TEP (tensor expert parallel) and DEP (data expert parallel) configs with the vllm backend
|
2026-01-14 13:13:44 -08:00 |
|
Tushar Sharma
|
cf433e6825
|
chore: update all copyright headers in repo to 2026 (#5130)
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
|
2026-01-02 22:08:23 +00:00 |
|
Hongkuan Zhou
|
b24ccd2906
|
feat: allow user to input gpu cost in profiler webui (#4935)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2025-12-12 12:15:01 -08:00 |
|
Hongkuan Zhou
|
ca0cd3b18a
|
feat: add webUI to profiler (#4544)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
|
2025-12-10 13:22:04 -08:00 |
|
Hongkuan Zhou
|
7750ed1a51
|
feat: add parallelization filters (#4144)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
|
2025-11-07 14:52:49 -05:00 |
|
Hongkuan Zhou
|
0b284b6348
|
feat: add cost plot to profiler (#4003)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2025-11-05 14:12:54 -08:00 |
|
Hongkuan Zhou
|
6243bcbe04
|
feat: support MoE model in SLA Planner Sglang (#3185)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
|
2025-09-23 19:42:43 -07:00 |
|
Hongkuan Zhou
|
fd358991ee
|
feat: standalone profiling script for a given endpoint (#2386)
|
2025-08-11 14:01:31 -07:00 |
|
Hongkuan Zhou
|
7ff100679e
|
refactor: break profile_sla into different files; feat: support vllm_v1 (#1588)
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
|
2025-06-18 12:11:55 -07:00 |