Roger Wang 16484d394c [Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475) ...

Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Sun Kim <sunytokki@gmail.com>
(cherry picked from commit f5f51e5931ffd99afe69696b60765b88d3eb13f2)

2025-12-16 17:15:49 -08:00

..

layers

[CustomOp] Extract ApplyRotaryEmb as CustomOp and unify the dispatch logic (#29873)

2025-12-16 17:13:23 -08:00

model_loader

[Model][Quantization] Restore MoE + GGUF models support (incl. Qwen3 MoE) by allowing Sideload Parameters (#30116)

2025-12-09 05:30:05 +00:00

models

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 17:15:49 -08:00

warmup

[BugFix] Fix AttributeError: 'MergedColumnParallelLinear' object has no attribute 'weight_scale' (#30399)

2025-12-10 07:59:23 -08:00

__init__.py

…

custom_op.py

[CustomOp] Support object-level enable for CustomOp (#30547)

2025-12-15 11:02:09 +08:00

parameter.py

…

utils.py

[Quantization] FP8 Weight Reloading for Quantized RL Rollout (#28480)

2025-12-09 13:54:32 -08:00