Skip to content

Actions: NVIDIA/TensorRT-Model-Optimizer

Actions

Unit tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
unit_tests.yml
819 workflow runs
819 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

add new trainer Unit tests #808: Pull request #352 synchronize by h-guo18
7m 51s haoguo/eagle-newtrainer
haoguo/eagle-newtrainer
7m 51s
add new trainer Unit tests #807: Pull request #352 synchronize by h-guo18
9m 21s haoguo/eagle-newtrainer
haoguo/eagle-newtrainer
9m 21s
Unit tests Unit tests #806: Scheduled
12m 26s main
main
12m 26s
add new trainer Unit tests #805: Pull request #352 synchronize by h-guo18
31m 4s haoguo/eagle-newtrainer
haoguo/eagle-newtrainer
31m 4s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #804: Pull request #359 synchronize by jenchen13
28m 27s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
28m 27s
Allow passing in DistillationConfig directly to setup fn (#399) Unit tests #803: Commit adcb1a1 pushed by AAnoosheh
15m 10s main
main
15m 10s
Bugfix for bmm style expert nvfp4 weight scale export (#384) Unit tests #802: Commit baf55f2 pushed by Edwardf0t1
12m 35s main
main
12m 35s
Allow passing in DistillationConfig directly to setup fn Unit tests #801: Pull request #399 opened by AAnoosheh
27m 21s aanoosheh/kd-direct-config
aanoosheh/kd-direct-config
27m 21s
Fixed FP8 fake quantization to use fp32 amax scaling; Added support f… Unit tests #800: Commit 71d1036 pushed by kevalmorabia97
12m 21s release/0.37.0
release/0.37.0
12m 21s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #799: Pull request #342 synchronize by jingyu-ml
32m 7s jingyux/megatron-lora
jingyux/megatron-lora
32m 7s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #798: Pull request #391 synchronize by yeyu-nvidia
26m 0s yeyu/kv_cache
yeyu/kv_cache
26m 0s
add new trainer Unit tests #797: Pull request #352 synchronize by h-guo18
27m 26s haoguo/eagle-newtrainer
haoguo/eagle-newtrainer
27m 26s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #796: Pull request #359 synchronize by jenchen13
27m 40s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
27m 40s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #795: Pull request #359 synchronize by jenchen13
8m 34s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
8m 34s
Unit tests Unit tests #794: Scheduled
12m 30s main
main
12m 30s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #793: Pull request #342 synchronize by jingyu-ml
27m 9s jingyux/megatron-lora
jingyux/megatron-lora
27m 9s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #792: Pull request #391 synchronize by yeyu-nvidia
31m 31s yeyu/kv_cache
yeyu/kv_cache
31m 31s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #791: Pull request #391 synchronize by yeyu-nvidia
18m 11s yeyu/kv_cache
yeyu/kv_cache
18m 11s
Fix: supporting gpt-oss HF eagle Unit tests #790: Pull request #398 synchronize by h-guo18
27m 48s haoguo/gptoss-fix
haoguo/gptoss-fix
27m 48s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #789: Pull request #391 synchronize by yeyu-nvidia
20m 43s yeyu/kv_cache
yeyu/kv_cache
20m 43s
Fix: supporting gpt-oss HF eagle Unit tests #788: Pull request #398 opened by h-guo18
9m 2s haoguo/gptoss-fix
haoguo/gptoss-fix
9m 2s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #787: Pull request #391 synchronize by yeyu-nvidia
29s yeyu/kv_cache
yeyu/kv_cache
29s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #786: Pull request #342 synchronize by jingyu-ml
27m 43s jingyux/megatron-lora
jingyux/megatron-lora
27m 43s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #785: Pull request #342 synchronize by jingyu-ml
3m 27s jingyux/megatron-lora
jingyux/megatron-lora
3m 27s
[1/N] ModelOPT PEFT mode support for the megatron-lm Unit tests #784: Pull request #342 synchronize by jingyu-ml
3m 13s jingyux/megatron-lora
jingyux/megatron-lora
3m 13s