diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml
index 2f5a84aaf1..ba8f382755 100644
--- a/.buildkite/test-amd.yaml
+++ b/.buildkite/test-amd.yaml
@@ -3335,36 +3335,6 @@ steps:
   commands:
     - pytest -v -s v1/e2e/test_hybrid_chunked_prefill.py
 
-#------------------------------------------------------  mi300 · weight_loading  -------------------------------------------------------#
-
-- label: ":amd: (MI300) Weight Loading Multi-GPU" # TBD
-  timeout_in_minutes: 70
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
-  dind: false
-  agent_pool: mi300_2
-  num_gpus: 2
-  working_dir: "/vllm-workspace/tests"
-  source_file_dependencies:
-  - vllm/
-  - tests/weight_loading
-  optional: true
-  commands:
-  - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-amd.txt
-
-- label: ":amd: (MI300) Weight Loading Multi-GPU (Large Models)" # TBD
-  timeout_in_minutes: 35
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
-  dind: false
-  agent_pool: mi300_2
-  num_gpus: 2
-  optional: true
-  working_dir: "/vllm-workspace/tests"
-  source_file_dependencies:
-  - vllm/
-  - tests/weight_loading
-  commands:
-  - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large-amd.txt
-
 #########################################################################################################################################
 #                                                                                                                                       #
 #                                                         MI355 (gfx950) tests                                                          #
@@ -4719,36 +4689,6 @@ steps:
   - if [ "$$BUILDKITE_PARALLEL_JOB" = "1" ]; then pytest -v -s "v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[False]"; fi
   - if [ "$$BUILDKITE_PARALLEL_JOB" = "2" ]; then pytest -v -s "v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[True]"; fi
 
-#------------------------------------------------------  mi355 · weight_loading  -------------------------------------------------------#
-
-- label: ":amd: (MI355) Weight Loading Multi-GPU" # TBD
-  timeout_in_minutes: 70
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
-  dind: false
-  agent_pool: mi355_2
-  num_gpus: 2
-  working_dir: "/vllm-workspace/tests"
-  source_file_dependencies:
-  - vllm/
-  - tests/weight_loading
-  optional: true
-  commands:
-  - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-amd.txt
-
-- label: ":amd: (MI355) Weight Loading Multi-GPU (Large Models)" # TBD
-  timeout_in_minutes: 30
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
-  dind: false
-  agent_pool: mi355_2
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/weight_loading
-  commands:
-  - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large-amd.txt
-
 #-----------------------------------------------------------  mi355 · misc  ------------------------------------------------------------#
 
 - label: ":amd: (MI355) Regression" # TBD
diff --git a/.buildkite/test_areas/weight_loading.yaml b/.buildkite/test_areas/weight_loading.yaml
deleted file mode 100644
index b8afa261e5..0000000000
--- a/.buildkite/test_areas/weight_loading.yaml
+++ /dev/null
@@ -1,38 +0,0 @@
-group: Weight Loading
-depends_on: 
-  - image-build
-steps:
-- label: ":nvidia: (L4) Weight Loading Multi-GPU"
-  key: weight-loading-multiple-gpu
-  timeout_in_minutes: 50
-  working_dir: "/vllm-workspace/tests"
-  device: l4
-  num_devices: 2
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - "!vllm/distributed/kv_transfer/"
-  - tests/weight_loading
-  commands:
-    - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models.txt
-  mirror:
-    amd:
-      label: ":amd: (MI355) Weight Loading Multi-GPU"
-      dind: false
-      device: mi355_2
-      timeout_in_minutes: 70
-      depends_on:
-      - image-build-amd
-      commands:
-      - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-amd.txt
-
-# - label: Weight Loading Multiple GPU - Large Models # optional
-#   working_dir: "/vllm-workspace/tests"
-#   num_devices: 2
-#   device: a100
-#   optional: true
-#   source_file_dependencies:
-#   - vllm/
-#   - tests/weight_loading
-#   commands:
-#     - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large.txt
diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS
index aa5b2a9fc9..f64cf5f561 100644
--- a/.github/CODEOWNERS
+++ b/.github/CODEOWNERS
@@ -110,7 +110,6 @@
 /tests/entrypoints/llm/test_struct_output_generate.py @mgoin @aarnphm @arpera
 /tests/v1/structured_output @mgoin @aarnphm @arpera
 /tests/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery @ivanium
-/tests/weight_loading @mgoin @youkaichao @yewentao256
 /tests/lora @jeejeelee
 /tests/models/language/generation/test_hybrid.py @tdoublep @tomeras91
 /tests/v1/kv_connector/nixl_integration @NickLucche
diff --git a/tests/kernels/quantization/test_rocm_compressed_tensors_w4a16.py b/tests/kernels/quantization/test_rocm_compressed_tensors_w4a16.py
index a9b35a4ea6..8e4563ab80 100644
--- a/tests/kernels/quantization/test_rocm_compressed_tensors_w4a16.py
+++ b/tests/kernels/quantization/test_rocm_compressed_tensors_w4a16.py
@@ -17,7 +17,6 @@ from vllm.platforms import current_platform
 @pytest.mark.parametrize(
     "model_path",
     [
-        # Listed in tests/weight_loading/models.txt
         "nm-testing/tinyllama-oneshot-w4a16-group128-v2",
     ],
 )
diff --git a/tests/weight_loading/models-amd.txt b/tests/weight_loading/models-amd.txt
deleted file mode 100644
index a6a85736cb..0000000000
--- a/tests/weight_loading/models-amd.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-# quantization, model, revision[, minimum capability[, safetensors load strategy]]
-fp8, amd/Meta-Llama-3.1-8B-Instruct-FP8-KV, main
-None, amd/Llama-3.2-1B-Instruct-FP8-KV, main
-fp8, amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV, main, 80, prefetch
-gptq, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
-gptq, TheBloke/Llama-2-7B-GPTQ, main
-gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
-compressed-tensors, nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8-channel-a8-tensor, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w4a16-group128-v2, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8a16-per-channel, main
-compressed-tensors, nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test, main
-compressed-tensors, nm-testing/Phi-3-mini-128k-instruct-FP8, main
-compressed-tensors, neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16, main
-awq, casperhansen/mixtral-instruct-awq, main
-fp8, neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV, main
diff --git a/tests/weight_loading/models-large-amd.txt b/tests/weight_loading/models-large-amd.txt
deleted file mode 100644
index 41e8ee5200..0000000000
--- a/tests/weight_loading/models-large-amd.txt
+++ /dev/null
@@ -1,4 +0,0 @@
-# quantization, model, revision[, minimum capability[, safetensors load strategy]]
-fp8, amd/Meta-Llama-3.1-70B-Instruct-FP8-KV, main, 80, prefetch
-None, microsoft/phi-4, main, 80, prefetch
-fp8, amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV, main, 80, prefetch
diff --git a/tests/weight_loading/models-large.txt b/tests/weight_loading/models-large.txt
deleted file mode 100644
index 8b3913cc2d..0000000000
--- a/tests/weight_loading/models-large.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-quantized, main
-compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized, main
-compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A16-quantized, main
-gptq, TheBloke/Mixtral-8x7B-v0.1-GPTQ, main
-awq_marlin, casperhansen/deepseek-coder-v2-instruct-awq, main
-compressed-tensors, RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16, main
diff --git a/tests/weight_loading/models.txt b/tests/weight_loading/models.txt
deleted file mode 100644
index 87b9650870..0000000000
--- a/tests/weight_loading/models.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-gptq, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
-gptq, TheBloke/Llama-2-7B-GPTQ, main
-gptq, LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit, main
-gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
-gptq, TechxGenus/gemma-2b-it-GPTQ, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8-channel-a8-tensor, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w4a16-group128-v2, main
-compressed-tensors, nm-testing/tinyllama-oneshot-w8a16-per-channel, main
-compressed-tensors, nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test, main
-compressed-tensors, nm-testing/Phi-3-mini-128k-instruct-FP8, main
-compressed-tensors, neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16, main
-#compressed-tensors, mgoin/DeepSeek-Coder-V2-Lite-Instruct-FP8, main
-awq, casperhansen/mixtral-instruct-awq, main
-awq_marlin, casperhansen/mixtral-instruct-awq, main
-fp8, neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV, main
diff --git a/tests/weight_loading/run_model_weight_loading_test.sh b/tests/weight_loading/run_model_weight_loading_test.sh
deleted file mode 100755
index 598f1620c7..0000000000
--- a/tests/weight_loading/run_model_weight_loading_test.sh
+++ /dev/null
@@ -1,58 +0,0 @@
-#!/bin/bash
-SUCCESS=0
-
-while getopts "c:" OPT; do
-  case ${OPT} in
-    c )
-        CONFIG="$OPTARG"
-        ;;
-    \? )
-        usage
-        exit 1
-        ;;
-  esac
-done
-
-
-IFS=$'\n' read -d '' -r -a MODEL_CONFIGS < "$CONFIG"
-
-for MODEL_CONFIG in "${MODEL_CONFIGS[@]}"
-do
-    if [[ $MODEL_CONFIG == \#* ]]; then
-        echo "=== SKIPPING MODEL: $MODEL_CONFIG ==="
-        continue
-    fi
-
-    LOCAL_SUCCESS=0
-    IFS=', ' read -r -a array <<< "$MODEL_CONFIG"
-
-    echo "=== RUNNING MODEL: $MODEL_CONFIG ==="
-
-    unset WEIGHT_LOADING_TEST_SAFETENSORS_LOAD_STRATEGY
-    export QUANTIZATION=${array[0]}
-    export MODEL_NAME=${array[1]}
-    export REVISION=${array[2]}
-    # If array length is larger than 3, then MIN_CAPABILITY is provided
-    if [ ${#array[@]} -gt 3 ]; then
-        export MIN_CAPABILITY=${array[3]}
-    fi
-    if [ ${#array[@]} -gt 4 ]; then
-        export WEIGHT_LOADING_TEST_SAFETENSORS_LOAD_STRATEGY=${array[4]}
-    fi
-    pytest -s weight_loading/test_weight_loading.py || LOCAL_SUCCESS=$?
-
-    if [[ $LOCAL_SUCCESS == 0 ]]; then
-        echo "=== PASSED MODEL: ${MODEL_CONFIG} ==="
-    else
-        echo "=== FAILED MODEL: ${MODEL_CONFIG} ==="
-    fi
-
-    SUCCESS=$((SUCCESS + LOCAL_SUCCESS))
-
-done
-
-if [ "${SUCCESS}" -eq "0" ]; then
-    exit 0
-else
-    exit 1
-fi
diff --git a/tests/weight_loading/test_weight_loading.py b/tests/weight_loading/test_weight_loading.py
deleted file mode 100644
index c32ce71aca..0000000000
--- a/tests/weight_loading/test_weight_loading.py
+++ /dev/null
@@ -1,49 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import os
-
-import pytest
-import torch
-
-from vllm.platforms import current_platform
-from vllm.utils.mem_constants import GiB_bytes
-
-MAX_MODEL_LEN = 1024
-MODEL_NAME = os.environ.get(
-    "MODEL_NAME", "robertgshaw2/zephyr-7b-beta-channelwise-gptq"
-)
-REVISION = os.environ.get("REVISION", "main")
-QUANTIZATION = os.environ.get("QUANTIZATION", "gptq_marlin")
-MIN_CAPABILITY = os.environ.get("MIN_CAPABILITY", "80")
-SAFETENSORS_LOAD_STRATEGY = os.environ.get(
-    "WEIGHT_LOADING_TEST_SAFETENSORS_LOAD_STRATEGY"
-)
-
-
-@pytest.mark.skipif(
-    MODEL_NAME == "casperhansen/deepseek-coder-v2-instruct-awq", reason="OOM in the CI"
-)
-@pytest.mark.skipif(
-    not current_platform.has_device_capability(int(MIN_CAPABILITY)),
-    reason="Current system does not have minimum capability.",
-)
-def test_weight_loading(vllm_runner):
-    """Test parameter weight loading with tp>1."""
-    # MoE models need fp16.
-    NEEDS_FP16 = QUANTIZATION == "gptq"
-    with vllm_runner(
-        model_name=MODEL_NAME,
-        revision=REVISION,
-        dtype=torch.half if NEEDS_FP16 else "auto",
-        quantization=None if QUANTIZATION == "None" else QUANTIZATION,
-        max_model_len=MAX_MODEL_LEN,
-        tensor_parallel_size=2,
-        safetensors_load_strategy=SAFETENSORS_LOAD_STRATEGY,
-        # Generating 20 tokens needs a tiny KV cache, while sizing and
-        # allocating a full-size one dominates this test on large devices.
-        kv_cache_memory_bytes=2 * GiB_bytes,
-    ) as model:
-        output = model.generate_greedy("Hello world!", max_tokens=20)
-        print(output)
-        assert output