Preetha/weight sharing fix #545
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
preetha-intel
requested review from
javier-intel,
sfatimar,
saurabhkale17 and
vthaniel
vthaniel
requested changes
Jan 23, 2025
ankitm3k
force-pushed
the
openvino/ep-weight-sharing
branch
2 times, most recently
from
a7fdeca to
c9fb7e0
Compare
preetha-intel
force-pushed
the
preetha/weight-sharing-fix
branch
from
dbe14b5 to
4fc48eb
Compare
|
LGTM |
ankitm3k
force-pushed
the
openvino/ep-weight-sharing
branch
from
48ee137 to
6d1f1cf
Compare
preetha-intel
force-pushed
the
preetha/weight-sharing-fix
branch
from
dc68414 to
42812a3
Compare
preetha-intel
force-pushed
the
preetha/weight-sharing-fix
branch
from
42812a3 to
df46642
Compare
preetha-intel
merged commit 7179a0b
into
openvino/ep-weight-sharing
6 of 16 checks passed
sfatimar
added a commit
that referenced
this pull request
Jan 27, 2025
* Rename EP instance context as session_context * Add support for GetEpContextNodes * enable config option for ovep weight sharing * add config option for ovep weight sharing * Refactor the conditional blocks in OVEP for compilation * Convert initializers with external data to graph inputs * create, store and export metadata for ovep weight sharing * fix error handling in weight sharing * fix crash issue while setting up inputs for wai model * pass weight sharing option to OVEP qdq stripping pass * Aligning OVEP variable names to match the session option value they hold * Add plumbing for context sharing plus refactoring around option handling * Store metadata in shared context * fix: fix provider options * create ov tensor from meta data and external data * create ov tensor * Add support for binding weight as input tensors * Fix for mapping subgraph to ov compiled network arguments * Fix for using so_share_ep_contexts without ep.context* flags * Add remote tensor support for NPU weight sharing * Use a single ov::Core copy across OVEP * Decouple provider option cache_dir from session option ep.context_file_path * Add support for serialization and deserialization of metadata to disk * Load blobs from relative path stored in ep_cache_context * Use remote L0 tensors for shared weights * fix linux ci issues * fix ci issues * Fix Windows build failure * Use ifstream to load weights instead of mmaped file * Fix for epctx models made up entirely of OVEP epctx nodes * Limit ov::Core lifetime to that of provider object * Enforce shared tensors cleanup on shutdown * Add support for default device type based on project configuration * fix: Fixed concrete_backend_ pointer double free issue on Linux * Preetha/weight sharing fix (#545) * Move variables from subgraph to session context for model specific properties * Fix for redundant subgraph creation * Remove unused variable --------- Co-authored-by: Javier E. Martinez <javier.e.martinez@intel.com> Co-authored-by: saurabhkale117 <saurabh1.kale@intel.com> Co-authored-by: Preetha Veeramalai <preetha.veeramalai@intel.com> Co-authored-by: ankitm3k <ankit.maheshkar@intel.com> Co-authored-by: Eric Crawford <eric.r.crawford@intel.com>
sfatimar
added a commit
that referenced
this pull request
Jan 31, 2025
* Rename EP instance context as session_context * Add support for GetEpContextNodes * enable config option for ovep weight sharing * add config option for ovep weight sharing * Refactor the conditional blocks in OVEP for compilation * Convert initializers with external data to graph inputs * create, store and export metadata for ovep weight sharing * fix error handling in weight sharing * fix crash issue while setting up inputs for wai model * pass weight sharing option to OVEP qdq stripping pass * Aligning OVEP variable names to match the session option value they hold * Add plumbing for context sharing plus refactoring around option handling * Store metadata in shared context * fix: fix provider options * create ov tensor from meta data and external data * create ov tensor * Add support for binding weight as input tensors * Fix for mapping subgraph to ov compiled network arguments * Fix for using so_share_ep_contexts without ep.context* flags * Add remote tensor support for NPU weight sharing * Use a single ov::Core copy across OVEP * Decouple provider option cache_dir from session option ep.context_file_path * Add support for serialization and deserialization of metadata to disk * Load blobs from relative path stored in ep_cache_context * Use remote L0 tensors for shared weights * fix linux ci issues * fix ci issues * Fix Windows build failure * Use ifstream to load weights instead of mmaped file * Fix for epctx models made up entirely of OVEP epctx nodes * Limit ov::Core lifetime to that of provider object * Enforce shared tensors cleanup on shutdown * Add support for default device type based on project configuration * fix: Fixed concrete_backend_ pointer double free issue on Linux * Preetha/weight sharing fix (#545) * Move variables from subgraph to session context for model specific properties * Fix for redundant subgraph creation * Remove unused variable --------- Co-authored-by: Javier E. Martinez <javier.e.martinez@intel.com> Co-authored-by: saurabhkale117 <saurabh1.kale@intel.com> Co-authored-by: Preetha Veeramalai <preetha.veeramalai@intel.com> Co-authored-by: ankitm3k <ankit.maheshkar@intel.com> Co-authored-by: Eric Crawford <eric.r.crawford@intel.com>
sfatimar
added a commit
that referenced
this pull request
Jan 31, 2025
* Rename EP instance context as session_context * Add support for GetEpContextNodes * enable config option for ovep weight sharing * add config option for ovep weight sharing * Refactor the conditional blocks in OVEP for compilation * Convert initializers with external data to graph inputs * create, store and export metadata for ovep weight sharing * fix error handling in weight sharing * fix crash issue while setting up inputs for wai model * pass weight sharing option to OVEP qdq stripping pass * Aligning OVEP variable names to match the session option value they hold * Add plumbing for context sharing plus refactoring around option handling * Store metadata in shared context * fix: fix provider options * create ov tensor from meta data and external data * create ov tensor * Add support for binding weight as input tensors * Fix for mapping subgraph to ov compiled network arguments * Fix for using so_share_ep_contexts without ep.context* flags * Add remote tensor support for NPU weight sharing * Use a single ov::Core copy across OVEP * Decouple provider option cache_dir from session option ep.context_file_path * Add support for serialization and deserialization of metadata to disk * Load blobs from relative path stored in ep_cache_context * Use remote L0 tensors for shared weights * fix linux ci issues * fix ci issues * Fix Windows build failure * Use ifstream to load weights instead of mmaped file * Fix for epctx models made up entirely of OVEP epctx nodes * Limit ov::Core lifetime to that of provider object * Enforce shared tensors cleanup on shutdown * Add support for default device type based on project configuration * fix: Fixed concrete_backend_ pointer double free issue on Linux * Preetha/weight sharing fix (#545) * Move variables from subgraph to session context for model specific properties * Fix for redundant subgraph creation * Remove unused variable --------- Co-authored-by: Javier E. Martinez <javier.e.martinez@intel.com> Co-authored-by: saurabhkale117 <saurabh1.kale@intel.com> Co-authored-by: Preetha Veeramalai <preetha.veeramalai@intel.com> Co-authored-by: ankitm3k <ankit.maheshkar@intel.com> Co-authored-by: Eric Crawford <eric.r.crawford@intel.com>
ankitm3k
added a commit
that referenced
this pull request
Jan 31, 2025
* Rename EP instance context as session_context * Add support for GetEpContextNodes * enable config option for ovep weight sharing * add config option for ovep weight sharing * Refactor the conditional blocks in OVEP for compilation * Convert initializers with external data to graph inputs * create, store and export metadata for ovep weight sharing * fix error handling in weight sharing * fix crash issue while setting up inputs for wai model * pass weight sharing option to OVEP qdq stripping pass * Aligning OVEP variable names to match the session option value they hold * Add plumbing for context sharing plus refactoring around option handling * Store metadata in shared context * fix: fix provider options * create ov tensor from meta data and external data * create ov tensor * Add support for binding weight as input tensors * Fix for mapping subgraph to ov compiled network arguments * Fix for using so_share_ep_contexts without ep.context* flags * Add remote tensor support for NPU weight sharing * Use a single ov::Core copy across OVEP * Decouple provider option cache_dir from session option ep.context_file_path * Add support for serialization and deserialization of metadata to disk * Load blobs from relative path stored in ep_cache_context * Use remote L0 tensors for shared weights * fix linux ci issues * fix ci issues * Fix Windows build failure * Use ifstream to load weights instead of mmaped file * Fix for epctx models made up entirely of OVEP epctx nodes * Limit ov::Core lifetime to that of provider object * Enforce shared tensors cleanup on shutdown * Add support for default device type based on project configuration * fix: Fixed concrete_backend_ pointer double free issue on Linux * Preetha/weight sharing fix (#545) * Move variables from subgraph to session context for model specific properties * Fix for redundant subgraph creation * Remove unused variable --------- Co-authored-by: Javier E. Martinez <javier.e.martinez@intel.com> Co-authored-by: saurabhkale117 <saurabh1.kale@intel.com> Co-authored-by: Preetha Veeramalai <preetha.veeramalai@intel.com> Co-authored-by: ankitm3k <ankit.maheshkar@intel.com> Co-authored-by: Eric Crawford <eric.r.crawford@intel.com>
ankitm3k
added a commit
that referenced
this pull request
Jan 31, 2025
* Rename EP instance context as session_context * Add support for GetEpContextNodes * enable config option for ovep weight sharing * add config option for ovep weight sharing * Refactor the conditional blocks in OVEP for compilation * Convert initializers with external data to graph inputs * create, store and export metadata for ovep weight sharing * fix error handling in weight sharing * fix crash issue while setting up inputs for wai model * pass weight sharing option to OVEP qdq stripping pass * Aligning OVEP variable names to match the session option value they hold * Add plumbing for context sharing plus refactoring around option handling * Store metadata in shared context * fix: fix provider options * create ov tensor from meta data and external data * create ov tensor * Add support for binding weight as input tensors * Fix for mapping subgraph to ov compiled network arguments * Fix for using so_share_ep_contexts without ep.context* flags * Add remote tensor support for NPU weight sharing * Use a single ov::Core copy across OVEP * Decouple provider option cache_dir from session option ep.context_file_path * Add support for serialization and deserialization of metadata to disk * Load blobs from relative path stored in ep_cache_context * Use remote L0 tensors for shared weights * fix linux ci issues * fix ci issues * Fix Windows build failure * Use ifstream to load weights instead of mmaped file * Fix for epctx models made up entirely of OVEP epctx nodes * Limit ov::Core lifetime to that of provider object * Enforce shared tensors cleanup on shutdown * Add support for default device type based on project configuration * fix: Fixed concrete_backend_ pointer double free issue on Linux * Preetha/weight sharing fix (#545) * Move variables from subgraph to session context for model specific properties * Fix for redundant subgraph creation * Remove unused variable --------- Co-authored-by: Javier E. Martinez <javier.e.martinez@intel.com> Co-authored-by: saurabhkale117 <saurabh1.kale@intel.com> Co-authored-by: Preetha Veeramalai <preetha.veeramalai@intel.com> Co-authored-by: ankitm3k <ankit.maheshkar@intel.com> Co-authored-by: Eric Crawford <eric.r.crawford@intel.com>
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
Move variables from subgraph to session context
Reduce redundant check with OVEP Get capability at backend manager
Bug fix for duplicate outputs with epctx model
Bug fix to set default compile time device option if runtime option is not provided.