Kurt Shuster 2991dd3d22 [Bugfix][Model] Support LoRA on Qwen3 Output Embedding (#29816) ...

Signed-off-by: kurt <kurt@thinkingmachines.ai>

2026-02-06 20:25:31 +08:00

..

__init__.py

…

conftest.py

[Feat] allow inplace loading lora (#31326)

2026-01-20 10:15:20 +08:00

test_add_lora.py

…

test_chatglm3_tp.py

…

test_deepseekv2_tp.py

…

test_default_mm_loras.py

…

test_fused_moe_lora_kernel.py

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

test_gptoss_tp.py

[Bugfix] Fix Triton FusedMoE LoRA (#30585)

2026-01-09 11:46:59 +00:00

test_layers.py

Add support for LoRA adapters in Nemotron-H models (#30802)

2026-01-19 22:30:44 +08:00

test_llama_tp.py

…

test_llm_with_multi_loras.py

[Feat] allow inplace loading lora (#31326)

2026-01-20 10:15:20 +08:00

test_lora_checkpoints.py

…

test_lora_functions.py

…

test_lora_huggingface.py

…

test_lora_manager.py

[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)

2026-01-08 15:20:49 -08:00

test_minicpmv_tp.py

…

test_mixtral.py

…

test_moe_lora_align_sum.py

…

test_olmoe_tp.py

…

test_peft_helper.py

…

test_punica_ops.py

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

test_quant_model.py

…

test_qwen3_unembed.py

[Bugfix][Model] Support LoRA on Qwen3 Output Embedding (#29816)

2026-02-06 20:25:31 +08:00

test_qwen3moe_tp.py

…

test_qwenvl.py

…

test_resolver.py

…

test_transformers_model.py

…

test_utils.py

…

test_worker.py

…

utils.py

…