Enable Llama2 70B to run with hqt on single card#50
Merged
Conversation
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
Yantom1
changed the title
MrGeva
suggested changes
Feb 19, 2024
MrGeva
approved these changes
Feb 20, 2024
bhargaveede
pushed a commit
that referenced
this pull request
Feb 22, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 5, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 5, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 5, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 5, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 5, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 11, 2024
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM. Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.
HolyFalafel
added a commit
that referenced
this pull request
Mar 24, 2024
Co-authored-by: Yan Tomsinsky <73292515+Yantom1@users.noreply.github.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Add disk_offload flag that controls device_map=auto. Setting this flag enbales weights offload to disk when cpu memory runs OOM.
Add const serialization path flag that gets a path for where to serialize const sections, so if there is no space on device to save all const sections they will be offloaded to disk.