Skip to content

Actions: NVIDIA/Model-Optimizer

Actions

Code Quality

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
code_quality.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Fix AutoCast unknown dimension metadata Code Quality #10725: Pull request #2420 synchronize by haoxiz-nvidia
4m 49s haoxiz/autocast-mismatch
haoxiz/autocast-mismatch
4m 49s
Fix AutoCast unknown dimension metadata Code Quality #10724: Pull request #2420 opened by haoxiz-nvidia
4m 41s haoxiz/autocast-mismatch
haoxiz/autocast-mismatch
4m 41s
Env: update onnxruntime and cuda flag Code Quality #10723: Pull request #2419 synchronize by haoxiz-nvidia
5m 8s haoxiz/env-fix
haoxiz/env-fix
5m 8s
Env: update onnxruntime and cuda flag Code Quality #10722: Pull request #2419 opened by haoxiz-nvidia
4m 47s haoxiz/env-fix
haoxiz/env-fix
4m 47s
[6721556] Fix mixed dtypes in NVFP4 FP16 ONNX export Code Quality #10721: Pull request #2415 synchronize by ajrasane
4m 33s ajrasane/nvbug-6721556-swin-mixed-dtype-add
ajrasane/nvbug-6721556-swin-mixed-dtype-add
4m 33s
[6466805] Add Dynamo ONNX export support for quantized models Code Quality #10720: Pull request #2418 opened by ajrasane
5m 7s ajrasane/dynamo-onnx-export
ajrasane/dynamo-onnx-export
5m 7s
[OMNIML-5570] 2/2 Compose GEMM and KV-cache AutoQuant workflows Code Quality #10719: Pull request #2273 synchronize by meenchen
4m 1s agent/kv-autoquant-composition
agent/kv-autoquant-composition
4m 1s
[5565357] Fix SDXL NVFP4 export and performance Code Quality #10718: Pull request #2336 synchronize by ajrasane
4m 31s arasane/fix_sdxl_nvfp4_export
arasane/fix_sdxl_nvfp4_export
4m 31s
docs: add Local Hessian NVFP4 weight-scale announcement blog Code Quality #10717: Pull request #2417 synchronize by realAsma
5m 14s asma/local_hessian_blog
asma/local_hessian_blog
5m 14s
docs: add Local Hessian NVFP4 weight-scale announcement blog Code Quality #10716: Pull request #2417 synchronize by realAsma
41s asma/local_hessian_blog
asma/local_hessian_blog
41s
Fix distributed AutoQuantize scoring and share backward setup Code Quality #10715: Pull request #2231 synchronize by realAsma
Action required joshua-hill:fix/autoquant-scoring-infrastructure
joshua-hill:fix/autoquant-scoring-infrastructure
Action required
[OMNIML-5899] Add IQ1_S and IQ2_XS quantization and unified checkpoint export Code Quality #10714: Pull request #2381 synchronize by ChenhanYu
4m 13s iq2xs-unified-export
iq2xs-unified-export
4m 13s
[5565357] Fix SDXL NVFP4 export and performance Code Quality #10713: Pull request #2336 synchronize by ajrasane
5m 16s arasane/fix_sdxl_nvfp4_export
arasane/fix_sdxl_nvfp4_export
5m 16s
PTQ reliability fixes: checkpoint resume + exclude_modules sentinel corruption Code Quality #10712: Pull request #2129 synchronize by wyattearp
Action required wyattearp:ptq-reliability-fixes
wyattearp:ptq-reliability-fixes
Action required
docs: add Local Hessian NVFP4 weight-scale announcement blog Code Quality #10711: Pull request #2417 synchronize by realAsma
5m 25s asma/local_hessian_blog
asma/local_hessian_blog
5m 25s
docs: add Local Hessian NVFP4 weight-scale announcement blog Code Quality #10710: Pull request #2417 synchronize by realAsma
1m 3s asma/local_hessian_blog
asma/local_hessian_blog
1m 3s
[5565357] Fix SDXL NVFP4 export and performance Code Quality #10709: Pull request #2336 synchronize by ajrasane
4m 11s arasane/fix_sdxl_nvfp4_export
arasane/fix_sdxl_nvfp4_export
4m 11s
[5612316][OMNIML-2983] Fix FP8 QDQ placement for delegated diffusion attention Code Quality #10708: Pull request #2416 synchronize by ajrasane
4m 18s ajrasane/nvbug-5612316-fp8-attention-qdq
ajrasane/nvbug-5612316-fp8-attention-qdq
4m 18s
Code Quality Code Quality #10707: Scheduled
4m 4s main
main
4m 4s
Fix vLLM fakequant calibration for hybrid attention models Code Quality #10706: Pull request #2414 synchronize by kinjalpatel27
4m 59s kinjal/fix_vllm_0.28
kinjal/fix_vllm_0.28
4m 59s
Fix vLLM fakequant calibration for hybrid attention models Code Quality #10705: Pull request #2414 synchronize by kinjalpatel27
4m 2s kinjal/fix_vllm_0.28
kinjal/fix_vllm_0.28
4m 2s
[OMNIML-5570] 2/2 Compose GEMM and KV-cache AutoQuant workflows Code Quality #10704: Pull request #2273 synchronize by meenchen
5m 27s agent/kv-autoquant-composition
agent/kv-autoquant-composition
5m 27s
docs: add Local Hessian NVFP4 weight-scale announcement blog Code Quality #10703: Pull request #2417 synchronize by realAsma
4m 17s asma/local_hessian_blog
asma/local_hessian_blog
4m 17s
[6463897] Fix narrow FP16 histogram calibration Code Quality #10702: Pull request #2412 synchronize by ajrasane
4m 53s ajrasane/nvbug-6463897-histogram-range
ajrasane/nvbug-6463897-histogram-range
4m 53s
[6721556] Fix mixed dtypes in NVFP4 FP16 ONNX export Code Quality #10701: Pull request #2415 synchronize by ajrasane
3m 59s ajrasane/nvbug-6721556-swin-mixed-dtype-add
ajrasane/nvbug-6721556-swin-mixed-dtype-add
3m 59s