Skip to content

feat: Support Mistral Small 3.1 24B VLM in TRT workflow #4183

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.

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
merged 1 commit into from
May 13, 2025

Conversation

brb-nv
Copy link
Collaborator

@brb-nv brb-nv commented May 9, 2025

Description

# Build TRT engine for vision encoder.
$ rm -rf mistral_mm_eng/ && python examples/models/core/multimodal/build_multimodal_engine.py --model_path /home/bbuddharaju/scratch/random/hf_models/Mistral-Small-3.1-24B-Instruct-2503/ --model_type pixtral --max_batch_size 8 --output_dir mistral_mm_eng/vision/

# Create TRTLLM checkpoint for the LLM decoder.
$ rm -rf mistral_mm_llm_ckpt/ && python examples/models/core/llama/convert_checkpoint.py --model_dir /home/bbuddharaju/scratch/random/hf_models/Mistral-Small-3.1-24B-Instruct-2503/ --output_dir mistral_mm_llm_ckpt/ --dtype bfloat16

# Build TRT engine for LLM decoder.
$ 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

# Run the entire pipeline.
$ python examples/models/core/multimodal/run.py --hf_model_dir /home/bbuddharaju/scratch/random/hf_models/Mistral-Small-3.1-24B-Instruct-2503/ --engine_dir mistral_mm_eng/ --visual_engine_name model.engine --batch_size 1 --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:1-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 brb-nv force-pushed the user/brb/mistral-small-vlm branch from 446d12c to 6b96b7d Compare May 9, 2025 18:49
@brb-nv brb-nv force-pushed the user/brb/mistral-small-vlm branch 3 times, most recently from 2522e92 to 162331f Compare May 9, 2025 18:59
@brb-nv
Copy link
Collaborator Author

brb-nv commented May 9, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4734 [ run ] triggered by Bot

@brb-nv brb-nv requested review from tijyojwad and amukkara May 9, 2025 19:41
@tensorrt-cicd
Copy link
Collaborator

PR_Github #4734 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #3416 completed with status: 'FAILURE'

@brb-nv brb-nv changed the title feat: Support for Mistral Small 3.1 24B VLM feat: Support Mistral Small 3.1 24B VLM in TRT workflow May 12, 2025
@brb-nv brb-nv force-pushed the user/brb/mistral-small-vlm branch from 162331f to 6bc8c39 Compare May 12, 2025 21:23
@brb-nv
Copy link
Collaborator Author

brb-nv commented May 12, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4913 [ run ] triggered by Bot

@brb-nv
Copy link
Collaborator Author

brb-nv commented May 13, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4953 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4913 [ run ] completed with state ABORTED

@brb-nv brb-nv requested a review from amukkara May 13, 2025 04:57
@brb-nv brb-nv force-pushed the user/brb/mistral-small-vlm branch 2 times, most recently from 2af78ba to 35c1ea5 Compare May 13, 2025 04:58
@brb-nv
Copy link
Collaborator Author

brb-nv commented May 13, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4957 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4953 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4957 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3599 completed with status: 'FAILURE'

@brb-nv brb-nv force-pushed the user/brb/mistral-small-vlm branch 2 times, most recently from d038f54 to 7d26224 Compare May 13, 2025 17:16
@brb-nv
Copy link
Collaborator Author

brb-nv commented May 13, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5049 [ run ] triggered by Bot

Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
@brb-nv brb-nv force-pushed the user/brb/mistral-small-vlm branch from 046970c to 7cadbe2 Compare May 13, 2025 19:03
@amukkara
Copy link
Collaborator

/bot kill

@amukkara amukkara enabled auto-merge (squash) May 13, 2025 19:17
@amukkara
Copy link
Collaborator

/bot skip --comment "Unrelated failed tests in last CI run are waived on main currently."

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5056 [ kill ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5059 [ ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5049 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5056 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit 7cadbe2

@amukkara
Copy link
Collaborator

/bot skip --comment "Unrelated failed tests in last CI run are waived on main currently."

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5061 [ skip ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5061 [ skip ] completed with state SUCCESS
Skipping testing for commit 7cadbe2

@amukkara amukkara merged commit cd5b3d2 into NVIDIA:main May 13, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants