Schwinn Saereesitthipitak b7c5baf63d fix: keep DeepSeek V4 RoPE cache on inv_freq device (#43926) ...

Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com>

2026-06-05 02:30:29 +04:00

..

kernels

[Quant] Support compressed-tensors WNA8O8Int linears and WNInt embeddings (#44340)

2026-06-04 07:40:33 -07:00

layers

fix: keep DeepSeek V4 RoPE cache on inv_freq device (#43926)

2026-06-05 02:30:29 +04:00

model_loader

[Bugfix] Convert Gemma4-MM ViT linear layers to vllm native impl (#43798)

2026-06-01 21:41:16 -07:00

models

[mamba] unify KDA conv states into one cache to match 2-state SSM layout (#44539)

2026-06-04 20:38:05 +02:00

offloader

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

warmup

[CI failure] Temporarily disable using persistent cache for flashinfer autotune (#43119)

2026-05-19 11:44:32 -07:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

parameter.py

[Quantization] add humming quantization kernel (#34556)

2026-04-24 09:29:44 -04:00

utils.py

[Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update. (#40390)

2026-05-06 10:32:26 +00:00