diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index 76aa5f7a35d..a37bdb0f4d9 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -13,6 +13,7 @@ /vllm/model_executor/guided_decoding @mgoin @russellb /vllm/multimodal @DarkLight1337 @ywang96 /vllm/vllm_flash_attn @LucasWilkinson +/vllm/lora @jeejeelee CMakeLists.txt @tlrmchlsmth # vLLM V1 @@ -40,3 +41,4 @@ CMakeLists.txt @tlrmchlsmth /tests/v1/entrypoints/llm/test_struct_output_generate.py @mgoin @russellb /tests/v1/structured_output @mgoin @russellb /tests/weight_loading @mgoin @youkaichao +/tests/lora @jeejeelee diff --git a/tests/quantization/test_bitsandbytes.py b/tests/quantization/test_bitsandbytes.py index 0f20f42d865..e8ddfd7fc77 100644 --- a/tests/quantization/test_bitsandbytes.py +++ b/tests/quantization/test_bitsandbytes.py @@ -37,12 +37,6 @@ ("yec019/fbopt-350m-8bit", "read pre-quantized 8-bit opt model"), ] -models_pre_quant_8bit_to_test = [ - ('meta-llama/Llama-Guard-3-8B-INT8', - 'read pre-quantized llama 8-bit model'), - ("yec019/fbopt-350m-8bit", "read pre-quantized 8-bit opt model"), -] - @pytest.mark.skipif(not is_quant_method_supported("bitsandbytes"), reason='bitsandbytes is not supported on this GPU type.')