[TRTLLM-4932] Add LLM API accuracy tests for Llama-4-Maverick-17B-128E-Instruct - FP8 variant #4389
Conversation
moraxu
force-pushed
the
add-cli-acc-tests-Llama-4-Maverick-17B-128E-Instruct
branch
from
620a81c to
f6bac27
Compare
|
/bot run |
|
PR_Github #6042 [ run ] triggered by Bot |
|
PR_Github #6042 [ run ] completed with state |
|
/bot run |
|
/bot kill |
|
Tracked in https://nvbugspro.nvidia.com/bug/5270247 |
moraxu
changed the title
|
PR_Github #6104 [ run ] triggered by Bot |
|
PR_Github #6106 [ kill ] triggered by Bot |
|
PR_Github #6104 [ run ] completed with state |
|
PR_Github #6106 [ kill ] completed with state |
Signed-off-by: moraxu <[email protected]>
Signed-off-by: moraxu <[email protected]>
Signed-off-by: Michal Guzek <[email protected]>
Signed-off-by: moraxu <[email protected]>
Signed-off-by: moraxu <[email protected]>
moraxu
force-pushed
the
add-cli-acc-tests-Llama-4-Maverick-17B-128E-Instruct
branch
from
7db0444 to
8c67f1e
Compare
📝 WalkthroughWalkthroughA new quantization configuration using FP8 was added for the Llama-4-Maverick-17B-128E-Instruct model. Corresponding integration tests targeting this configuration were introduced, including a new test method and updates to test lists to ensure coverage of FP8 pre-quantized and auto dtype scenarios for this model variant. Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant LLM
participant Tasks
TestRunner->>LLM: Load pre-quantized FP8 model (Llama-4-Maverick-17B-128E-Instruct)
TestRunner->>LLM: Configure parallelism (tp_size, pp_size, ep_size), cuda_graph
TestRunner->>Tasks: Run MMLU task on LLM
Tasks-->>TestRunner: Return MMLU results
TestRunner->>Tasks: Run GSM8K task on LLM
Tasks-->>TestRunner: Return GSM8K results
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. ✨ Finishing Touches
🧪 Generate unit tests
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tests/integration/defs/accuracy/references/mmlu.yaml(1 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(1 hunks)tests/integration/test_lists/qa/llm_sanity_test.txt(1 hunks)
🧰 Additional context used
🧠 Learnings (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
Learnt from: amitz-nv
PR: #5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.402Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks is_adapter_in_cpu_cache() and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.
Learnt from: yechank-nvidia
PR: #6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using from_shared_tensor() is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call strip_for_generation() to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
🔇 Additional comments (2)
tests/integration/defs/accuracy/references/mmlu.yaml (1)
69-71: Verify placeholder accuracy update planPlease confirm that the new FP8 entry uses a placeholder accuracy intentionally and that there’s a process or reminder in place to replace
accuracy: 0.0with real measured values once tests complete.Locations to review:
- tests/integration/defs/accuracy/references/mmlu.yaml (lines 69–71):
- quant_algo: FP8 kv_cache_quant_algo: FP8 accuracy: 0.0- For reference, the existing microsoft/Phi-4-mini-instruct-tp2 entry also uses
accuracy: 0.0and is tracked with:# TODO: update once https://nvbugs/5393849 is fixed. microsoft/Phi-4-mini-instruct-tp2: - accuracy: 0.0Can you either add a similar TODO comment above this new block or confirm where the placeholder will be tracked for future updates?
tests/integration/test_lists/qa/llm_sanity_test.txt (1)
38-40: LGTM! Well-structured test additions.The new test entries follow the established patterns and naming conventions. Good practice to include both the new
test_fp8_prequantizedtest and the existingtest_auto_dtypetest for comprehensive coverage across both PyTorch API and CLI flow execution paths.
4 participants
Description
Add LLM API accuracy tests for Llama-4-Maverick-17B-128E-Instruct - FP8 variant.
Test Coverage
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.
Details
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
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.
Summary by CodeRabbit
New Features
Tests