Schwinn Saereesitthipitak
|
a6d970e961
|
feat: refactor GMS client memory manager with tiered API (#6549)
|
2026-02-25 23:24:17 +00:00 |
|
Schwinn Saereesitthipitak
|
a55b2433f7
|
fix: remove unnecessary cuda synchronize calls in GMS adapters (#6362)
|
2026-02-18 09:30:55 -08:00 |
|
dagil-nvidia
|
0ef41ffe03
|
refactor: use tempfile module instead of hardcoded /tmp paths (#5789)
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-09 21:44:03 +00:00 |
|
Biswa Panda
|
4f9a190ca2
|
docs: add overview doc for GPU Memory Service (GMS) (#5920)
Co-authored-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
|
2026-02-03 17:22:01 -08:00 |
|
Schwinn Saereesitthipitak
|
69fdc9dd87
|
fix: CUDA synchronization to prevent sleep/wake race conditions (#5759)
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
|
2026-01-29 16:13:43 -08:00 |
|
Schwinn Saereesitthipitak
|
a2fbda3e1c
|
feat(sglang): integration with GPU Memory Service (#5664)
Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com>
|
2026-01-29 09:19:59 -08:00 |
|
Schwinn Saereesitthipitak
|
2ef408ffd3
|
fix: gpu memory service cli not found (#5749)
|
2026-01-28 19:38:00 +00:00 |
|
Pavithra Vijayakrishnan
|
66c369964a
|
chore: version update for 0.9.0 (#5661)
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
|
2026-01-26 17:18:05 -08:00 |
|
Schwinn Saereesitthipitak
|
ccd12d1cad
|
feat: vLLM integrations for GPU Memory Service (#5615)
|
2026-01-26 20:50:30 +00:00 |
|
Schwinn Saereesitthipitak
|
f976f02b85
|
refactor: rename sleep/wake endpoints for consistency (#5629)
|
2026-01-26 08:52:40 -08:00 |
|
Schwinn Saereesitthipitak
|
92ecd308fd
|
refactor: move GMS to standalone component (#5616)
|
2026-01-24 00:28:41 +00:00 |
|
Schwinn Saereesitthipitak
|
30c6228b82
|
feat: GPU Memory Service (#5286)
Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com>
|
2026-01-23 09:50:09 +00:00 |