[None][infra] Bump version to 1.2.0rc6.post4 (#12857)

Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>

Author: yuanjingx87

README.md

@@ -10,7 +10,7 @@ state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.<
 [![python](https://img.shields.io/badge/python-3.10-green)](https://www.python.org/downloads/release/python-31012/)
 [![cuda](https://img.shields.io/badge/cuda-13.0.0-green)](https://developer.nvidia.com/cuda-downloads)
 [![torch](https://img.shields.io/badge/torch-2.9.0-green)](https://pytorch.org)
-[![version](https://img.shields.io/badge/release-1.2.0rc6.post2-green)](https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/version.py)
+[![version](https://img.shields.io/badge/release-1.2.0rc6.post4-green)](https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/version.py)
 [![license](https://img.shields.io/badge/license-Apache%202-blue)](https://github.com/NVIDIA/TensorRT-LLM/blob/main/LICENSE)
 
 [Architecture](https://nvidia.github.io/TensorRT-LLM/developer-guide/overview.html)&nbsp;&nbsp;&nbsp;|&nbsp;&nbsp;&nbsp;[Performance](https://nvidia.github.io/TensorRT-LLM/developer-guide/perf-overview.html)&nbsp;&nbsp;&nbsp;|&nbsp;&nbsp;&nbsp;[Examples](https://nvidia.github.io/TensorRT-LLM/quick-start-guide.html)&nbsp;&nbsp;&nbsp;|&nbsp;&nbsp;&nbsp;[Documentation](https://nvidia.github.io/TensorRT-LLM/)&nbsp;&nbsp;&nbsp;|&nbsp;&nbsp;&nbsp;[Roadmap](https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap)

examples/constraints.txt

@@ -1,3 +1,3 @@
-tensorrt_llm==1.2.0rc6.post2
+tensorrt_llm==1.2.0rc6.post4
 evaluate~=0.4.1
 rouge_score~=0.1.2

jenkins/L0_Test.groovy

@@ -2944,8 +2944,8 @@ def launchTestJobs(pipeline, testFilter)
         "DGX_H100-4_GPUs-PyTorch-Others-1": ["dgx-h100-x4-oci", "l0_dgx_h100", 1, 1, 4],
         "B300-PyTorch-1": ["b300-single", "l0_b300", 1, 1],
         "DGX_B200-4_GPUs-PyTorch-1": ["b200-x4", "l0_dgx_b200", 1, 1, 4],
-        "DGX_B200-4_GPUs-PyTorch-Ray-1": ["b200-x4-lbd", "l0_dgx_b200", 1, 1, 4, 1, true],
-        "DGX_B200-8_GPUs-PyTorch-1": ["b200-x8-lbd", "l0_dgx_b200", 1, 1, 8, 1, true],
+        "DGX_B200-4_GPUs-PyTorch-Ray-1": ["b200-x4", "l0_dgx_b200", 1, 1, 4, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-1": ["b200-x8", "l0_dgx_b200", 1, 1, 8, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Post-Merge-1": ["b200-trtllm", "l0_dgx_b200", 1, 2, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Post-Merge-2": ["b200-trtllm", "l0_dgx_b200", 2, 2, 4, 1, true],
         "DGX_B300-4_GPUs-PyTorch-Post-Merge-1": ["b300-x4", "l0_dgx_b300", 1, 2, 4],

tensorrt_llm/version.py

@@ -12,4 +12,4 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-__version__ = "1.2.0rc6.post2"
+__version__ = "1.2.0rc6.post4"