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

Set git commit signing on in .vscode/settings.json Unit tests #728: Pull request #393 opened by kevalmorabia97
28m 37s kmorabia/git-signing
kmorabia/git-signing
28m 37s
Add HF_TOKEN secret to example_tests workflow Unit tests #727: Pull request #392 opened by kevalmorabia97
28m 36s kevalmorabia97-patch-1
kevalmorabia97-patch-1
28m 36s
Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization Unit tests #726: Pull request #381 synchronize by realAsma
26m 14s asma/fp8_fakequant_fix
asma/fp8_fakequant_fix
26m 14s
Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] Unit tests #725: Pull request #359 synchronize by jenchen13
26m 39s jennifchen/cp_amax_sync
jennifchen/cp_amax_sync
26m 39s
Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization Unit tests #724: Pull request #381 synchronize by realAsma
29s asma/fp8_fakequant_fix
asma/fp8_fakequant_fix
29s
Updated Prune-KD NeMo flow Unit tests #723: Pull request #382 synchronize by AAnoosheh
28m 6s aanoosheh/pkd_slurm
aanoosheh/pkd_slurm
28m 6s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #722: Pull request #391 synchronize by yeyu-nvidia
26m 49s yeyu/kv_cache
yeyu/kv_cache
26m 49s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #721: Pull request #391 synchronize by yeyu-nvidia
26m 52s yeyu/kv_cache
yeyu/kv_cache
26m 52s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #720: Pull request #391 synchronize by yeyu-nvidia
1m 32s yeyu/kv_cache
yeyu/kv_cache
1m 32s
EAGLE parallel draft with auto regression; kv cache in EAGLE training Unit tests #719: Pull request #391 opened by yeyu-nvidia
4m 40s yeyu/kv_cache
yeyu/kv_cache
4m 40s
Fix FLOPs calculation Unit tests #718: Pull request #388 synchronize by Y-T-G
12m 40s Y-T-G:patch-1
Y-T-G:patch-1
12m 40s
Fix FLOPs calculation Unit tests #717: Pull request #388 synchronize by Y-T-G
Action required Y-T-G:patch-1
Y-T-G:patch-1
Action required
Remove Qwen tokenizer modification Unit tests #716: Pull request #390 opened by cjluo-nv
27m 15s chenjiel/remove_qwen_token
chenjiel/remove_qwen_token
27m 15s
Move phi4_mm warning to above Unit tests #715: Pull request #389 opened by cjluo-nv
27m 21s cjluo-nv-patch-1
cjluo-nv-patch-1
27m 21s
Fix FLOPs calculation Unit tests #714: Pull request #388 opened by Y-T-G
12m 41s Y-T-G:patch-1
Y-T-G:patch-1
12m 41s
[5545101]: AutoCast: Add options to force include node/op in F16 Unit tests #713: Pull request #386 synchronize by galagam
27m 48s galagam:dev-gagam-force-input-nodes
galagam:dev-gagam-force-input-nodes
27m 48s
Unit tests Unit tests #712: Scheduled
12m 26s main
main
12m 26s
[5545101]: AutoCast: Add options to force include node/op in F16 Unit tests #711: Pull request #386 synchronize by galagam
30m 6s galagam:dev-gagam-force-input-nodes
galagam:dev-gagam-force-input-nodes
30m 6s
[5545101]: AutoCast: Add options to force include node/op in F16 Unit tests #710: Pull request #386 synchronize by galagam
21m 4s galagam:dev-gagam-force-input-nodes
galagam:dev-gagam-force-input-nodes
21m 4s
[5545101]: AutoCast: Add options to force include node/op in F16 Unit tests #709: Pull request #386 opened by galagam
52s galagam:dev-gagam-force-input-nodes
galagam:dev-gagam-force-input-nodes
52s
Unit tests Unit tests #708: Scheduled
12m 34s main
main
12m 34s
Bugfix for bmm style expert nvfp4 weight scale export Unit tests #707: Pull request #384 synchronize by Edwardf0t1
27m 56s zhiyu/fix-bmm-experts-nvfp4-export
zhiyu/fix-bmm-experts-nvfp4-export
27m 56s
Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization Unit tests #706: Pull request #381 synchronize by realAsma
22m 46s asma/fp8_fakequant_fix
asma/fp8_fakequant_fix
22m 46s
Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization Unit tests #705: Pull request #381 synchronize by realAsma
22m 56s asma/fp8_fakequant_fix
asma/fp8_fakequant_fix
22m 56s
Bugfix for bmm style expert nvfp4 weight scale export Unit tests #704: Pull request #384 opened by Edwardf0t1
29s zhiyu/fix-bmm-experts-nvfp4-export
zhiyu/fix-bmm-experts-nvfp4-export
29s