[NPUW] Update NPUW caching properties #31876
Open
+66
−64
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This was referenced Aug 26, 2025
dmatveev
reviewed
Aug 26, 2025
| DEFINE_OPT(NPUW_LLM_CACHE_ROPE, bool, true, npuw::llm::cache_rope, CompileTime); | ||
| DEFINE_OPT(NPUW_LLM_CACHE_ROPE, bool, true, npuw::llm::cache_rope, RunTime); |
There was a problem hiding this comment.
It impacts the IR that's being compiled, how it is a runtime option?
There was a problem hiding this comment.
All of our properties are RunTime. CompileTime is used for the NPU compiler. Also caching property won't work if it's not RunTime since we would to define isAvailable in filteredConfig somewhere in the plugin
| DEFINE_OPT(NPUW_LLM_SHARED_HEAD, bool, true, npuw::llm::shared_lm_head, CompileTime); | ||
| DEFINE_OPT(NPUW_LLM_SHARED_HEAD, bool, true, npuw::llm::shared_lm_head, RunTime); |
There was a problem hiding this comment.
Answered above
Comment on lines
250
to
251
| struct NPUW_LLM_ADDITIONAL_PREFILL_CONFIG final : OptionBase<NPUW_LLM_ADDITIONAL_PREFILL_CONFIG, ov::AnyMap> { | ||
| static std::string_view key() { |
There was a problem hiding this comment.
To support caching for any additional configs we might pass
smirnov-alexey
commented
Aug 26, 2025
| @@ -276,4 +306,95 @@ struct NPUW_LLM_GENERATE_CONFIG final : OptionBase<NPUW_LLM_GENERATE_CONFIG, ov: | |||
| return false; | |||
| } | |||
| }; | |||
|
|
|||
| struct NPUW_LLM_ADDITIONAL_GENERATE_CONFIG final : OptionBase<NPUW_LLM_ADDITIONAL_GENERATE_CONFIG, ov::AnyMap> { | |||
There was a problem hiding this comment.
Move under macro
|
build_jenkins |
dmatveev
approved these changes
Aug 28, 2025
|
build_jenkins |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.