608405e0e7
feat: harden ManagedProcess teardown, add xdist-safe tests ( #6670 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
2026-03-13 12:54:37 -07:00
761e848b5b
fix: Fix mocker+router segfaults + reliability fixes ( #7162 )
...
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
2026-03-10 22:39:06 -07:00
df67ce16c5
fix: increase process group termination timeout from 2s to 8s ( #7132 )
...
Signed-off-by: Yuewei Na <yna@nvidia.com>
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
2026-03-09 16:35:00 -07:00
fddbb84dcf
fix: snapshot children before process group kill to prevent GPU memory leaks ( #7122 )
...
Signed-off-by: Yuewei Na <yna@nvidia.com>
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
2026-03-09 15:55:43 -07:00
d86937f955
test: relocate test output to /tmp to keep git working tree clean ( #6289 )
...
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-17 21:21:01 -08:00
1ffa489ea1
refactor: Move --migration-limit flag from backend to frontend ( #5918 )
...
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
2026-02-06 20:50:55 +00:00
e55ebec562
chore: rename terminate_existing to terminate_all_matching_processes ( #5923 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2026-02-04 09:50:41 -08:00
aea57caeb5
fix: fix test process termination logic to properly trigger graceful shutdown ( #5775 )
2026-01-31 02:51:53 +00:00
584020f4b3
chore: consistently used the arc shared workers configs + CI flake fixes ( #5707 )
...
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-01-29 09:29:24 +00:00
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
2804479989
refactor: frontend/test_vllm.py to use shared dynamic ports ( #5013 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-19 12:39:15 -08:00
c22280ccf4
refactor: frontend/grpc tests to use dynamic ports ( #4992 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-18 16:21:28 -08:00
f10f59426d
refactor: consolidate fault_tolerance DynamoFrontendProcess, add timeouts ( #5008 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-17 21:25:23 -08:00
1b8869f5e7
refactor: router tests to be pytest-xdist parallel safe ( #5005 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-17 18:33:47 -08:00
6da23fcf79
test: make serve tests xdist-safe with dynamic ports ( #4951 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-16 09:15:24 -08:00
c6b440e498
test: add dynamic port allocation for fault_tolerant test execution ( #4835 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-10 23:11:09 -08:00
2472aa4ac1
test: add timeout markers to pytest.mark.gpu_1 serve tests ( #4768 )
...
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-05 17:10:53 -08:00
6bccf099f8
feat: deprecate DYN_SYSTEM_ENABLED in favor of DYN_SYSTEM_PORT ( #4082 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-11-07 15:31:51 -08:00
0028cdf43d
feat: Use ForwardPassCallback api from TRTLLM to register end of forward pass callback to enable cuda graphs ( #3297 )
...
Signed-off-by: Kyle McGill <kmcgill@nvidia.com>
2025-10-27 15:12:04 -07:00
9320816275
refactor: standardize e2e tests across 3 frameworks ( #2827 )
...
Signed-off-by: alec-flowers <aflowers@nvidia.com>
2025-09-08 23:31:27 +00:00
3c7c1d64ce
chore: pass in mocker engine args directly in python cli + default frontend port to 8000 ( #2853 )
...
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-09-04 04:26:00 +00:00
432c5b13f2
feat: Shutdown DRT when vLLM engine fails ( #2698 )
...
Signed-off-by: J Wyman <jwyman@nvidia.com>
2025-09-02 20:10:54 +00:00
8c2072cf34
fix: [trtllm] add wait_for_instance before register_llm ( #2683 )
...
Signed-off-by: alec-flowers <aflowers@nvidia.com>
2025-08-28 17:52:57 -07:00
9b9f2ce4f6
fix: pytest robustness and parsing error ( #2676 )
2025-08-24 10:13:41 -07:00
de7fe38b20
feat: add vllm e2e integration tests ( #1935 )
2025-07-15 04:47:12 +00:00
a9c0e0c7fa
fix: for handling zombie process ( #1801 )
2025-07-07 16:29:36 -07:00
36f03d40f1
test: fault tolerance tests ( #1444 )
...
Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-07-03 18:46:58 +00:00
cdddaedaf8
test: Add dynamo serve TRTLLM example to pytest ( #1417 )
2025-06-07 01:23:52 +00:00
373f1f38b5
test: basic end to end ( #1339 )
...
Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: pvijayakrish <pvijayakrish@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-06-05 20:22:36 +00:00
Keiven C