Netanel Haber 6ae4c8d6fc chunk parakeet into 30s clips to prevent OOMs on long audios (#36671) ...

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

2026-03-18 14:22:24 -07:00

..

kernels

[Torch 2.11] Guard torch._C._cpu attribute checks for forward compatibility (#35673)

2026-03-17 18:47:59 +00:00

layers

[Perf] Add tuned triton moe config for Qwen3.5 H200, 9.9% E2E throughput improvement (#37340)

2026-03-18 14:18:34 -04:00

model_loader

[Bugfix] Fix EP weight filter breaking EPLB and NVFP4 accuracy (#37322)

2026-03-18 18:30:29 +08:00

models

chunk parakeet into 30s clips to prevent OOMs on long audios (#36671)

2026-03-18 14:22:24 -07:00

offloader

Bugfix for offloading+prefetch for GLM-4.7-FP8 (#37178)

2026-03-17 21:22:09 +08:00

warmup

[Feature]: Remove Chunking From FusedMoE (#34086)

2026-03-12 14:24:38 -04:00

__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

[QeRL] Layerwise Reloading (#32133)

2026-01-30 08:50:05 -07:00

utils.py

[BugFix] Fix EPLB fail for MoeFP4 model with Marlin backend (#33262)

2026-01-29 16:52:11 +08:00