Commit Graph
9 Commits
Author SHA1 Message Date
Ata Fatahi 031f64aa1b Add e2e test for multi instance multi stage memory release/resume occupuation (#7208)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2025-06-26 17:40:38 -07:00
Ata Fatahi 1ab6be1b26 Purge VerlEngine (#7326)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2025-06-19 23:47:21 -07:00
Ata Fatahi b8318aec48 Make NCCL NVLS configurable (#3502) 2025-02-12 03:25:06 +08:00
Ata Fatahi ce094a5d79 Clean up GPU memory after killing sglang processes (#2457)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2024-12-17 03:42:40 -08:00
Ata Fatahi e3b3acfa6f Rename rust folder to sgl-router (#2464)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2024-12-12 09:40:41 -08:00
Ata Fatahi 6efa9e4a6d Bump sglang-router to 0.1.1 (#2459)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2024-12-11 17:40:03 -08:00
Ata FatahiandByron Hsu 7791fd9948 Include version info into the router package (#2456)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
2024-12-11 17:31:20 -08:00
Ata Fatahi 2ac36b9a7b Make request payload size configurable (#2444)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2024-12-11 16:55:21 -08:00
Ata Fatahi ed45e509df Check gpu availability at server args creation (#2340)
Signed-off-by: Ata Fatahi <immrata@gmail.com>
2024-12-05 01:53:02 +08:00