Skip to content

Actions: NVIDIA/TensorRT-Model-Optimizer

Actions

Unit tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
unit_tests.yml
815 workflow runs
815 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #779: Pull request #391 synchronize by yeyu-nvidia
3m 23s yeyu/kv_cache
yeyu/kv_cache
3m 23s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #778: Pull request #391 synchronize by yeyu-nvidia
15m 27s yeyu/kv_cache
yeyu/kv_cache
15m 27s
[5256037] Automatically infer calibration shapes for per node calibra… Unit tests #777: Commit 0d51156 pushed by ajrasane
13m 0s main
main
13m 0s
Minor pruning update Unit tests #776: Pull request #397 opened by kevalmorabia97
28m 9s kmorabia/pruning-update
kmorabia/pruning-update
28m 9s
Add HF_TOKEN for GPU tests in CICD Unit tests #775: Pull request #396 opened by kevalmorabia97
27m 48s kevalmorabia97-patch-1
kevalmorabia97-patch-1
27m 48s
[Autocast] Fix edge case casting input directly to output Unit tests #774: Pull request #305 synchronize by aboubezari
Action required aboubezari:fix_auto_cast_io_special_nodes_bug
aboubezari:fix_auto_cast_io_special_nodes_bug
Action required
Updated Prune-KD NeMo flow Unit tests #773: Pull request #382 synchronize by AAnoosheh
27m 11s aanoosheh/pkd_slurm
aanoosheh/pkd_slurm
27m 11s
Update ReadMe for torch_quant_to_onnx.py example Unit tests #772: Pull request #395 synchronize by ajrasane
27m 20s ajrasane/readme_update
ajrasane/readme_update
27m 20s
Unit tests Unit tests #771: Scheduled
12m 34s main
main
12m 34s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #770: Pull request #342 synchronize by jingyu-ml
26m 22s jingyux/megatron-lora
jingyux/megatron-lora
26m 22s
Update ReadMe for torch_quant_to_onnx.py example Unit tests #769: Pull request #395 opened by ajrasane
27m 25s ajrasane/readme_update
ajrasane/readme_update
27m 25s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #768: Pull request #342 synchronize by jingyu-ml
27m 7s jingyux/megatron-lora
jingyux/megatron-lora
27m 7s
[5256037] Automatically infer calibration shapes for per node calibration Unit tests #767: Pull request #394 synchronize by ajrasane
28m 2s ajrasane/input_shapes
ajrasane/input_shapes
28m 2s
[5256037] Automatically infer calibration shapes for per node calibration Unit tests #766: Pull request #394 opened by ajrasane
8m 10s ajrasane/input_shapes
ajrasane/input_shapes
8m 10s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #765: Pull request #342 synchronize by jingyu-ml
27m 40s jingyux/megatron-lora
jingyux/megatron-lora
27m 40s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #764: Pull request #359 synchronize by jenchen13
28m 23s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
28m 23s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #763: Pull request #359 synchronize by jenchen13
15m 1s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
15m 1s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #762: Pull request #359 synchronize by jenchen13
2m 29s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
2m 29s
FP8 Block quantize onnx export support Unit tests #761: Pull request #324 synchronize by jingyu-ml
26m 37s jingyux/block-quant-onnx
jingyux/block-quant-onnx
26m 37s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #760: Pull request #342 synchronize by jingyu-ml
26m 21s jingyux/megatron-lora
jingyux/megatron-lora
26m 21s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #759: Pull request #342 synchronize by jingyu-ml
16m 6s jingyux/megatron-lora
jingyux/megatron-lora
16m 6s
Move phi4_mm warning to above Unit tests #758: Pull request #389 synchronize by cjluo-nv
27m 18s cjluo-nv-patch-1
cjluo-nv-patch-1
27m 18s
Move phi4_mm warning to above Unit tests #757: Pull request #389 synchronize by cjluo-nv
31s cjluo-nv-patch-1
cjluo-nv-patch-1
31s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #756: Pull request #342 synchronize by jingyu-ml
28m 51s jingyux/megatron-lora
jingyux/megatron-lora
28m 51s
QLoRA DDP export Unit tests #755: Pull request #353 synchronize by sugunav14
26m 10s svelury/qlora-ddp-export
svelury/qlora-ddp-export
26m 10s