Skip to content

Update TensorRT-LLM version #829

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mc-nv merged 2 commits into from
Dec 17, 2025
Merged

Update TensorRT-LLM version #829

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fc73e2f
Update TensorRT-LLM version
mc-nv Dec 16, 2025
01b479e
Update dockerfile
mc-nv Dec 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions dockerfile/Dockerfile.triton.trt_llm_backend
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,8 +17,8 @@ ARG TORCH_VER=2.9.0a0+145a3a7bda.nv25.10
ARG TORCHVISION_VER=0.24.0a0+094e7af5

ARG TENSORRTLLM_REPO=https://github.com/NVIDIA/TensorRT-LLM.git
ARG TENSORRTLLM_REPO_TAG=release/1.0
ARG TENSORRTLLM_VER=1.2.0rc2
ARG TENSORRTLLM_REPO_TAG=release/1.1
ARG TENSORRTLLM_VER=1.1.0

FROM ${PYTORCH_IMAGE} AS pytorch_image
FROM ${BASE_IMAGE} AS install_dependencies
Expand Down
2 changes: 1 addition & 1 deletion tensorrt_llm
Open in desktop
Submodule tensorrt_llm updated 95 files
+3 −0 .github/CODEOWNERS
+1 −0 .github/pull_request_template.md
+108 −0 .github/tava_architecture_diagram.md
+2 −2 .pre-commit-config.yaml
+15,143 −0 ATTRIBUTIONS-CPP-aarch64.md
+14,951 −0 ATTRIBUTIONS-CPP-x86_64.md
+45,884 −0 ATTRIBUTIONS-Python.md
+3 −0 constraints.txt
+2 −0 cpp/tensorrt_llm/kernels/communicationKernels/mnnvlTwoShotAllreduceKernels.cu
+0 −4 cpp/tensorrt_llm/kernels/cutlass_kernels/fp8_blockscale_gemm/fp8_blockscale_tma_utils.cuh
+4 −5 cpp/tensorrt_llm/kernels/recoverFromRingAtten.cu
+6 −3 cpp/tensorrt_llm/kernels/trtllmGenKernels/gemm/KernelRunner.cpp
+4 −0 docker/Dockerfile.multi
+1 −1 docker/common/install_base.sh
+43 −24 docs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.md
+33 −10 docs/source/developer-guide/perf-benchmarking.md
+246 −229 docs/source/developer-guide/perf-overview.md
+4 −14 docs/source/examples/dynamo_k8s_example.rst
+6 −5 docs/source/features/quantization.md
+2 −1 docs/source/legacy/reference/support-matrix.md
+2 −2 docs/source/models/supported-models.md
+12 −12 docs/source/overview.md
+2 −0 docs/source/quick-start-guide.md
+107 −11 docs/source/release-notes.md
+3 −3 examples/auto_deploy/README.md
+40 −2 examples/llm-api/llm_mgmn_llm_distributed.sh
+38 −2 examples/llm-api/llm_mgmn_trtllm_bench.sh
+38 −2 examples/llm-api/llm_mgmn_trtllm_serve.sh
+4 −4 jenkins/current_image_tags.properties
+3 −2 requirements.txt
+16 −16 security_scanning/docs/poetry.lock
+1 −1 security_scanning/docs/pyproject.toml
+10 −11 security_scanning/examples/apps/poetry.lock
+19 −31 security_scanning/examples/auto_deploy/poetry.lock
+12 −24 security_scanning/examples/draft_target_model/poetry.lock
+12 −24 security_scanning/examples/eagle/poetry.lock
+12 −24 security_scanning/examples/llm-eval/lm-eval-harness/poetry.lock
+12 −24 security_scanning/examples/lookahead/poetry.lock
+12 −24 security_scanning/examples/medusa/poetry.lock
+161 −51 security_scanning/examples/models/contrib/baichuan/poetry.lock
+12 −24 security_scanning/examples/models/contrib/bloom/poetry.lock
+24 −36 security_scanning/examples/models/contrib/chatglm-6b/poetry.lock
+1 −1 security_scanning/examples/models/contrib/chatglm-6b/pyproject.toml
+24 −36 security_scanning/examples/models/contrib/chatglm2-6b/poetry.lock
+1 −1 security_scanning/examples/models/contrib/chatglm2-6b/pyproject.toml
+24 −36 security_scanning/examples/models/contrib/chatglm3-6b-32k/poetry.lock
+1 −1 security_scanning/examples/models/contrib/chatglm3-6b-32k/pyproject.toml
+12 −24 security_scanning/examples/models/contrib/dbrx/poetry.lock
+12 −24 security_scanning/examples/models/contrib/deepseek_v1/poetry.lock
+12 −24 security_scanning/examples/models/contrib/deepseek_v2/poetry.lock
+8 −8 security_scanning/examples/models/contrib/falcon/poetry.lock
+12 −24 security_scanning/examples/models/contrib/gptj/poetry.lock
+12 −24 security_scanning/examples/models/contrib/gptneox/poetry.lock
+27 −39 security_scanning/examples/models/contrib/grok/poetry.lock
+11 −23 security_scanning/examples/models/contrib/hyperclovax/poetry.lock
+12 −24 security_scanning/examples/models/contrib/internlm/poetry.lock
+12 −24 security_scanning/examples/models/contrib/jais/poetry.lock
+112 −18 security_scanning/examples/models/contrib/mmdit/poetry.lock
+12 −24 security_scanning/examples/models/contrib/mpt/poetry.lock
+12 −24 security_scanning/examples/models/contrib/opt/poetry.lock
+12 −24 security_scanning/examples/models/contrib/skywork/poetry.lock
+12 −24 security_scanning/examples/models/contrib/smaug/poetry.lock
+168 −167 security_scanning/examples/models/contrib/stdit/poetry.lock
+2 −2 security_scanning/examples/models/contrib/stdit/pyproject.toml
+12 −24 security_scanning/examples/models/core/commandr/poetry.lock
+29 −41 security_scanning/examples/models/core/gemma/poetry.lock
+24 −36 security_scanning/examples/models/core/glm-4-9b/poetry.lock
+1 −1 security_scanning/examples/models/core/glm-4-9b/pyproject.toml
+12 −24 security_scanning/examples/models/core/gpt/poetry.lock
+8 −8 security_scanning/examples/models/core/llama/poetry.lock
+8 −8 security_scanning/examples/models/core/mamba/poetry.lock
+9 −9 security_scanning/examples/models/core/mixtral/poetry.lock
+12 −12 security_scanning/examples/models/core/mllama/poetry.lock
+12 −24 security_scanning/examples/models/core/nemotron/poetry.lock
+12 −24 security_scanning/examples/models/core/phi/poetry.lock
+244 −253 security_scanning/examples/models/core/qwen/poetry.lock
+2 −2 security_scanning/examples/models/core/qwen/pyproject.toml
+8 −8 security_scanning/examples/models/core/qwen2audio/poetry.lock
+273 −171 security_scanning/examples/models/core/qwenvl/poetry.lock
+1 −1 security_scanning/examples/models/core/qwenvl/pyproject.toml
+19 −19 security_scanning/examples/models/core/recurrentgemma/poetry.lock
+57 −57 security_scanning/examples/models/core/whisper/poetry.lock
+1 −1 security_scanning/examples/models/core/whisper/pyproject.toml
+12 −24 security_scanning/examples/ngram/poetry.lock
+161 −51 security_scanning/examples/quantization/poetry.lock
+12 −24 security_scanning/examples/redrafter/poetry.lock
+12 −24 security_scanning/examples/trtllm-eval/poetry.lock
+248 −226 security_scanning/poetry.lock
+7 −6 security_scanning/pyproject.toml
+112 −120 security_scanning/tests/integration/defs/perf/poetry.lock
+1 −1 security_scanning/tests/integration/defs/perf/pyproject.toml
+9 −9 security_scanning/triton_backend/poetry.lock
+18 −10 tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
+2 −1 tensorrt_llm/_torch/pyexecutor/py_executor_creator.py
+1 −1 tests/integration/test_lists/waives.txt
Loading