sychen52andVadim Gimpelson d4d703caf9 [Bugfix][Model] Fix FP8 PLE loading in mixed ModelOpt checkpoints (#54882) ...

Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>

2026-09-03 21:09:39 +04:00

..

__init__.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_config.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_hc_ops.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_ple.py

[Bugfix][Model] Fix FP8 PLE loading in mixed ModelOpt checkpoints (#54882)

2026-09-03 21:09:39 +04:00

test_qsa_amd.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_qsa_pre_indexer.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_qsa_reference.py

[Qwen3.8-Flash-Next] Separate prefill and decode paths for QSA indexer (#54513)

2026-09-02 09:08:10 +08:00