LLM: Add XPU Memory Optimizations for Pipeline Parallel #11567
Merged
Conversation
This file contains 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
xiangyuT
changed the title
hkvision
approved these changes
Jul 15, 2024
plusbang
reviewed
Jul 15, 2024
| _enable_lowmem = os.getenv('IPEX_LLM_LOW_MEM') | ||
| _enable_lowmem = (_enable_lowmem is not None) and (_enable_lowmem.lower() == "1") | ||
| if _enable_lowmem: | ||
| model = low_mem_convert(model) |
There was a problem hiding this comment.
Not sure this memory optimization could also be added in single GPU inference case? Other LGTM.
There was a problem hiding this comment.
It could, but for single GPU current existing optimizations may be enough for the demands, so we don't override the CausalLM forward previously.
RyuKosei
pushed a commit
to RyuKosei/ipex-llm
that referenced
this pull request
Jul 19, 2024
…ics#11567) Add XPU Memory Optimizations for Pipeline Parallel
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Outdated suggestions cannot be applied.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.
Description
3. Summary of the change
Add model forward convert for llama, chatglm3/4 when
IPEX_LLM_LOW_MEMis set.4. How to test?
1234). And paste your action link here once it has been successfully finished.https://github.com/intel-analytics/ipex-llm-workflow/actions/runs/9900998189