Skip to content

Actions: NVIDIA/TensorRT-Model-Optimizer

Actions

GPU tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
gpu_tests.yml
543 workflow runs
543 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

TensorQuantizer: remove validation from forward path to reduce cpu-gp… GPU tests #368: Commit 4623fb0 pushed by copy-pr-bot bot
5m 37s pull-request/357
pull-request/357
5m 37s
Fix torch.onnx._internal imports for torch 2.9 GPU tests #367: Commit 0a4521a pushed by copy-pr-bot bot
1h 17m 27s pull-request/356
pull-request/356
1h 17m 27s
Fix torch.onnx._internal imports for torch 2.9 GPU tests #366: Commit a5cfedd pushed by copy-pr-bot bot
55s pull-request/356
pull-request/356
55s
GPU tests GPU tests #365: Scheduled
1h 30m 5s main
main
1h 30m 5s
add comments; make #ttt_steps configurable GPU tests #364: Commit 3415d15 pushed by copy-pr-bot bot
13m 21s pull-request/350
pull-request/350
13m 21s
empty GPU tests #363: Commit d364c25 pushed by copy-pr-bot bot
49s pull-request/350
pull-request/350
49s
add comments; make #ttt_steps configurable GPU tests #362: Commit 3415d15 pushed by copy-pr-bot bot
3m 46s pull-request/350
pull-request/350
3m 46s
fix bugs for unknown model_type of llava and fix path dependency for … GPU tests #361: Commit 42bb023 pushed by copy-pr-bot bot
20s pull-request/355
pull-request/355
20s
Remove OfflineEagleRegistry; Benjamin:Fix conversation ID indexing GPU tests #360: Commit 5add4cb pushed by copy-pr-bot bot
1h 20m 9s pull-request/300
pull-request/300
1h 20m 9s
Remove OfflineEagleRegistry; Benjamin:Fix conversation ID indexing GPU tests #359: Commit 338d0e3 pushed by copy-pr-bot bot
5m 38s pull-request/300
pull-request/300
5m 38s
Fix conversation ID indexing GPU tests #358: Commit bf8d1a8 pushed by copy-pr-bot bot
5m 35s pull-request/300
pull-request/300
5m 35s
Enable direct INT8/FP8 input in graph GPU tests #357: Commit 40dd0c5 pushed by copy-pr-bot bot
1h 33m 30s pull-request/354
pull-request/354
1h 33m 30s
revert GPU tests #356: Commit b8cc0de pushed by copy-pr-bot bot
1h 49m 47s pull-request/348
pull-request/348
1h 49m 47s
revert GPU tests #355: Commit f84d09a pushed by copy-pr-bot bot
57s pull-request/348
pull-request/348
57s
minor GPU tests #354: Commit 79c6a77 pushed by copy-pr-bot bot
2m 50s pull-request/348
pull-request/348
2m 50s
make new mask the same dtype and device as attn_mask GPU tests #353: Commit 66f5c67 pushed by copy-pr-bot bot
9m 9s pull-request/348
pull-request/348
9m 9s
Fix conversation ID indexing GPU tests #352: Commit 8708a77 pushed by copy-pr-bot bot
16m 15s pull-request/300
pull-request/300
16m 15s
Merge branch 'main' into jingyux/block-quant-onnx GPU tests #351: Commit 0a0ad7a pushed by copy-pr-bot bot
1h 48m 39s pull-request/324
pull-request/324
1h 48m 39s
GPU tests GPU tests #350: Scheduled
1h 7m 40s main
main
1h 7m 40s
add a copy_custom_model_files function in hf_ptq to copy essential py… GPU tests #349: Commit 962656f pushed by copy-pr-bot bot
15s pull-request/351
pull-request/351
15s
[5506930]Add support in ModelOpt for generating mixed-precision (INT4… GPU tests #348: Commit b069cec pushed by copy-pr-bot bot
1h 32m 38s pull-request/310
pull-request/310
1h 32m 38s
GPU tests GPU tests #347: Scheduled
1h 7m 48s main
main
1h 7m 48s
Add test cases GPU tests #346: Commit d9a79c1 pushed by copy-pr-bot bot
1h 16m 55s pull-request/342
pull-request/342
1h 16m 55s
GPU tests GPU tests #345: Scheduled
1h 7m 33s main
main
1h 7m 33s
fix: avoid deepcopy megatron model config GPU tests #344: Commit c8da426 pushed by copy-pr-bot bot
1h 35m 43s pull-request/349
pull-request/349
1h 35m 43s