Skip to content

Actions: NVIDIA/TensorRT-Model-Optimizer

Actions

GPU tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
gpu_tests.yml
723 workflow runs
723 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

cleanup GPU tests #473: Commit 7acbe57 pushed by copy-pr-bot bot
1h 24m 26s pull-request/384
pull-request/384
1h 24m 26s
Fixed FP8 fake quantization to use fp32 amax scaling GPU tests #472: Commit ce384be pushed by copy-pr-bot bot
2s pull-request/381
pull-request/381
2s
Fixed FP8 fake quantization to use fp32 amax scaling GPU tests #471: Commit d920b7f pushed by copy-pr-bot bot
45m 49s pull-request/381
pull-request/381
45m 49s
cleanup GPU tests #470: Commit 9dd1a3f pushed by copy-pr-bot bot
5m 31s pull-request/384
pull-request/384
5m 31s
GPU tests GPU tests #469: Scheduled
1h 14m 44s main
main
1h 14m 44s
Merge branch 'main' into jingyux/megatron-lora GPU tests #468: Commit 9c5bbdf pushed by copy-pr-bot bot
5m 37s pull-request/342
pull-request/342
5m 37s
Update GPU tests #467: Commit 8c59aca pushed by copy-pr-bot bot
1m 14s pull-request/342
pull-request/342
1m 14s
minor GPU tests #466: Commit 1e3df5f pushed by copy-pr-bot bot
5m 43s pull-request/381
pull-request/381
5m 43s
minor GPU tests #465: Commit 8415eb1 pushed by copy-pr-bot bot
4m 50s pull-request/381
pull-request/381
4m 50s
Update the grad for loras GPU tests #464: Commit ac164c0 pushed by copy-pr-bot bot
5m 33s pull-request/342
pull-request/342
5m 33s
minor GPU tests #463: Commit c4c32ba pushed by copy-pr-bot bot
5m 33s pull-request/381
pull-request/381
5m 33s
Use fp8_eager for cpu or if amax is None GPU tests #462: Commit 97dc2ef pushed by copy-pr-bot bot
5m 40s pull-request/381
pull-request/381
5m 40s
Fixed FP8 fake quantization to use fp32 amax scaling GPU tests #461: Commit ddbd66d pushed by copy-pr-bot bot
31m 7s pull-request/381
pull-request/381
31m 7s
Fixed FP8 fake quantization to use fp32 amax scaling GPU tests #460: Commit dfca83e pushed by copy-pr-bot bot
19m 14s pull-request/381
pull-request/381
19m 14s
More fix to the init GPU tests #459: Commit ea167ec pushed by copy-pr-bot bot
5m 33s pull-request/342
pull-request/342
5m 33s
more cleanups; make amax float32 by default GPU tests #458: Commit ee03094 pushed by copy-pr-bot bot
46m 54s pull-request/381
pull-request/381
46m 54s
More fix to the init GPU tests #457: Commit 3810be4 pushed by copy-pr-bot bot
5m 41s pull-request/342
pull-request/342
5m 41s
minors on the __init__ GPU tests #456: Commit 07c0345 pushed by copy-pr-bot bot
1m 40s pull-request/342
pull-request/342
1m 40s
Force to check the mcore model GPU tests #455: Commit 7ec3e5b pushed by copy-pr-bot bot
5m 31s pull-request/342
pull-request/342
5m 31s
Update lora implementations GPU tests #454: Commit 1eb6677 pushed by copy-pr-bot bot
5m 30s pull-request/342
pull-request/342
5m 30s
TensorQuantizer: remove validation from forward path to reduce cpu-gp… GPU tests #453: Commit b8e5ad2 pushed by copy-pr-bot bot
1h 43m 46s pull-request/357
pull-request/357
1h 43m 46s
address review feedbacks GPU tests #452: Commit 08c2628 pushed by copy-pr-bot bot
10m 4s pull-request/357
pull-request/357
10m 4s
Squashed commit GPU tests #451: Commit d632578 pushed by copy-pr-bot bot
20s pull-request/382
pull-request/382
20s
Squashed commit GPU tests #450: Commit eb4e041 pushed by copy-pr-bot bot
19s pull-request/382
pull-request/382
19s
minor GPU tests #449: Commit c80416a pushed by copy-pr-bot bot
1h 36m 21s pull-request/381
pull-request/381
1h 36m 21s
ProTip! You can narrow down the results and go further in time using created:<2025-09-26 or the other filters available.