fix: Mistral Small vision encoder with BS>1

[brb-nv]

Description

BS > 1 fails on TRTLLM main for vision encoder of Mistral Small 3.1 24B. This MR fixes that and adds functionality to run BS>1 inference in multimodal_model_runner.py.

$ rm -rf mistral_mm_eng/ && python examples/models/core/multimodal/build_multimodal_engine.py --model_path /home/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503/ --model_type pixtral --max_batch_size 8 --output_dir mistral_mm_eng/vision/
$ rm -rf mistral_mm_llm_ckpt/ && python examples/models/core/llama/convert_checkpoint.py --model_dir /home/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503/ --output_dir mistral_mm_llm_ckpt/ --dtype bfloat16
$ rm -rf mistral_mm_eng/llm/ && trtllm-build --checkpoint_dir mistral_mm_llm_ckpt/ --output_dir mistral_mm_eng/llm/ --max_batch_size 8 --max_input_len 131072 --max_seq_len 131072 --max_multimodal_len $((131072 * 8)) --use_paged_context_fmha enable
$ python examples/models/core/multimodal/run.py --hf_model_dir /home/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503/ --engine_dir mistral_mm_eng/ --visual_engine_name model.engine --batch_size 4 --enable_chunked_context --max_new_tokens 512 --temperature 0 --top_p 1 --lora_task_uids -1 --session python

Test Coverage

$ pytest tests/integration/defs/examples/test_multimodal.py::test_llm_multimodal_general[Mistral-Small-3.1-24B-Instruct-2503-pp:1-tp:1-bfloat16-bs:8-cpp_e2e:False-nb:1] -s -v

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

Launch build/test pipelines. All previously running jobs will be killed.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

[brb-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #6343 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #6343 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4631 completed with status: 'FAILURE'

[brb-nv]

/bot run

[tensorrt-cicd]

PR_Github #6668 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #6668 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4871 completed with status: 'FAILURE'

[brb-nv]

Closing this in favor of #4713.

I learnt that current process is to merge to release branch and let it be cherry-picked to main.