[https://nvbugs/5448579][fix] EXAONE-4.0 accuracy test bugfix #6888
Conversation
Signed-off-by: yechank <[email protected]>
📝 WalkthroughWalkthroughUpdated a test in tests/integration/defs/accuracy/test_llm_api_pytorch.py to simplify KvCacheConfig instantiation by removing the max_attention_window argument, keeping enable_block_reuse and enable_partial_reuse settings unchanged. No other logic or public interfaces were modified. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
|
/bot run |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
2375-2376: Change looks correct; add a brief WAR comment to document the rationale.Dropping max_attention_window and explicitly disabling both block and partial reuse matches the stated bugfix intent for EXAONE-4.0 and aligns with similar WARs elsewhere in this file. To aid future maintainers, add a short comment referencing the nvbugs context.
Apply this diff to document the reason:
- kv_cache_config = KvCacheConfig(enable_block_reuse=False, - enable_partial_reuse=False) + # WAR for EXAONE-4.0 accuracy (https://nvbugs/5448579): disable KV cache reuse. + kv_cache_config = KvCacheConfig(enable_block_reuse=False, + enable_partial_reuse=False)
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
|
PR_Github #15237 [ run ] triggered by Bot |
|
/bot run |
|
PR_Github #15551 [ run ] triggered by Bot |
|
PR_Github #15551 [ run ] completed with state |
Signed-off-by: yechank <[email protected]>
…#6888) Signed-off-by: yechank <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…#6888) Signed-off-by: yechank <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…#6888) Signed-off-by: yechank <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…#6888) Signed-off-by: yechank <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…#6888) Signed-off-by: yechank <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
3 participants
Summary by CodeRabbit