Julien DebacheandHarry Mellor 2bdae2a5a8 [fix] Mistral-Large-3 accuracy regression on main (#57563) ...

Signed-off-by: jdebache <jdebache@nvidia.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2026-09-18 14:19:16 +00:00

..

amd

[Bugfix][ROCm] Alias SparseAttnIndexerKpool.forward_cuda to forward_native (GLM-5.3-Flash boot crash) (#57425)

2026-09-18 03:36:55 +00:00

common

[fix] Mistral-Large-3 accuracy regression on main (#57563)

2026-09-18 14:19:16 +00:00

nvidia

[Perf][GLM5.3-Flash] Use cooperative top-k for small GLM decode batches (#57327)

2026-09-18 10:31:35 +08:00

__init__.py

[ROCm] [Bugfix] Enable Load and Inference of GLM-5.3-Flash Quark MXFP4 Checkpoint (#56176)

2026-09-16 01:25:29 +00:00

sparse_indexer.py

[Refactor][GLM-5.3-Flash] Move sparse_attn_indexer_kpool into the model folder and split AMD/NVIDIA (#55358)

2026-09-16 05:50:35 +00:00