Runkai TaoandJee Jee Li ada4f4fadd [Fix Bug]num_active_loras always equals to zero (#34119) ...

Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

2026-03-02 23:17:46 +08:00

..

__init__.py

[LoRA] Support Quantized Adapters (#30286)

2026-02-20 19:54:35 -08:00

fused_moe_lora_fp8_op.py

[LoRA] Support Quantized Adapters (#30286)

2026-02-20 19:54:35 -08:00

fused_moe_lora_op.py

[Fix Bug]num_active_loras always equals to zero (#34119)

2026-03-02 23:17:46 +08:00

kernel_utils.py

[Kernel] Optimization of the mm_k operator. (#28280)

2025-11-10 16:03:46 +00:00

lora_expand_op.py

[Fix Bug]num_active_loras always equals to zero (#34119)

2026-03-02 23:17:46 +08:00

lora_kernel_metadata.py

[Fix Bug]num_active_loras always equals to zero (#34119)

2026-03-02 23:17:46 +08:00

lora_shrink_op.py

[Fix Bug]num_active_loras always equals to zero (#34119)

2026-03-02 23:17:46 +08:00

README_TUNING.md

[Docs] Clean up README_TUNING.md (#28088)

2025-11-05 19:01:34 +00:00

utils.py

Add TMA support to fused_moe_lora kernel (#32195)

2026-03-01 10:55:25 +08:00