Disable nm-testing models with issues in CI (#28206)

Signed-off-by: mgoin <mgoin64@gmail.com>

.buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-W8A16-compressed-tensors.yaml

-# For vllm script, with -t option (tensor parallel size).
-# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise -b "auto" -l 1000 -f 5 -t 1
-model_name: "nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise"
-tasks:
-- name: "gsm8k"
-  metrics:
-  - name: "exact_match,strict-match"
-    value: 0.595
-  - name: "exact_match,flexible-extract"
-    value: 0.582
-limit: 1000
-num_fewshot: 5

benchmarks/kernels/benchmark_grouped_gemm_cutlass.py

@@ -16,8 +16,8 @@ from vllm.model_executor.layers.fused_moe.fused_moe import (
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 
 DEFAULT_MODELS = [
-    "nm-testing/Mixtral-8x7B-Instruct-v0.1",
-    "nm-testing/deepseekv2-lite",
+    "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "deepseek-ai/DeepSeek-V2-Lite",
     "ibm-granite/granite-3.0-1b-a400m",
     "ibm-granite/granite-3.0-3b-a800m",
 ]

benchmarks/kernels/benchmark_shapes.py

@@ -78,11 +78,11 @@ WEIGHT_SHAPES = {
 }
 
 WEIGHT_SHAPES_MOE = {
-    "nm-testing/Mixtral-8x7B-Instruct-v0.1": [
+    "mistralai/Mixtral-8x7B-Instruct-v0.1": [
         [8, 2, 4096, 28672],
         [8, 2, 14336, 4096],
     ],
-    "nm-testing/deepseekv2-lite": [
+    "deepseek-ai/DeepSeek-V2-Lite": [
         [64, 6, 2048, 1408],
     ],
     "ibm-granite/granite-3.0-1b-a400m": [