Expose Llama Fused OPs control from run_lora_clm.py#23
Merged
2 commits merged intoFeb 7, 2024
Merged
Conversation
vivekgoe
requested review from
bhargaveede,
libinta,
mandy-li and
ssarkar2
as code owners
Author
|
@dvarshney-habana please review, we have already reviewed it with Puneesh. |
ghost
approved these changes
Feb 7, 2024
ghost
merged commit
bhargaveede
pushed a commit
that referenced
this pull request
Feb 19, 2024
* Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments
bhargaveede
pushed a commit
that referenced
this pull request
Feb 19, 2024
* Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments
dudilester
pushed a commit
that referenced
this pull request
Feb 29, 2024
* Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments
hlahkar
pushed a commit
that referenced
this pull request
Mar 3, 2024
* Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments
vivekgoe
added
the
ported_to_hf_oh
bhargaveede
pushed a commit
that referenced
this pull request
Mar 8, 2024
Expose Llama Fused OPs control from run_lora_clm.py (#23) * Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments Co-authored-by: Vivek Goel <vgoel@habana.ai>
puneeshkhanna
pushed a commit
to puneeshkhanna/optimum-habana-fork
that referenced
this pull request
Mar 11, 2024
Expose Llama Fused OPs control from run_lora_clm.py (HabanaAI#23) * Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments Co-authored-by: Vivek Goel <vgoel@habana.ai>
HolyFalafel
pushed a commit
that referenced
this pull request
Mar 11, 2024
Expose Llama Fused OPs control from run_lora_clm.py (#23) * Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments Co-authored-by: Vivek Goel <vgoel@habana.ai>
kalyanjk
pushed a commit
to kalyanjk/optimum-habana-fork
that referenced
this pull request
Apr 12, 2024
* Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments
kalyanjk
pushed a commit
to kalyanjk/optimum-habana-fork
that referenced
this pull request
Apr 15, 2024
* Expose Llama Fused OPs control from run_lora_clm.py * Update as per review comments
astachowiczhabana
added a commit
that referenced
this pull request
Nov 22, 2024
* Fix clip test * Skip falcon tests * Fix clip test * [SW-209062] Disable default sdpa in Albert (#23) Transformers' default sdpa implementation caused performance drop in Albert. Adding Albert to the list of models which don't yet have sdpa implementation in Gaudi and use eager attention. * [SW-209210] skip first token in EOS check. (#25) (#27) * Problem: output of _sample function was filled with padding tokens for for bart model. * Cause: Bart model uses the same token as decoder_start_token_id and end of string. See: https://huggingface.co/facebook/bart-large-cnn/blob/main/config.json Because of that mechanism filling model output with padding tokens after EOS (end of string) toke was replacing whole response with padding. * Solution: Skip check for EOS for first token in padding filling loop. * Update CODEOWNERS * Adding labels clone as workaround to avoid crash (#28) * [SW-0] Fix style --------- Co-authored-by: Urszula Golowicz <urszula.golowicz@intel.com> Co-authored-by: Marcin Łapiński <mlapinskix@habana.ai> Co-authored-by: Bhargav <beede@habana.ai>
xinyu-intel
pushed a commit
that referenced
this pull request
Mar 4, 2025
* Fix clip test * Skip falcon tests * Fix clip test * [SW-209062] Disable default sdpa in Albert (#23) Transformers' default sdpa implementation caused performance drop in Albert. Adding Albert to the list of models which don't yet have sdpa implementation in Gaudi and use eager attention. * [SW-209210] skip first token in EOS check. (#25) (#27) * Problem: output of _sample function was filled with padding tokens for for bart model. * Cause: Bart model uses the same token as decoder_start_token_id and end of string. See: https://huggingface.co/facebook/bart-large-cnn/blob/main/config.json Because of that mechanism filling model output with padding tokens after EOS (end of string) toke was replacing whole response with padding. * Solution: Skip check for EOS for first token in padding filling loop. * Update CODEOWNERS * Adding labels clone as workaround to avoid crash (#28) * [SW-0] Fix style --------- Co-authored-by: Urszula Golowicz <urszula.golowicz@intel.com> Co-authored-by: Marcin Łapiński <mlapinskix@habana.ai> Co-authored-by: Bhargav <beede@habana.ai>
This pull request was closed.
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
2 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.
What does this PR do?
Exposes FusedRoPE enable/disable for Llama model from task scripts (currently done for only run_lora_clm.py). It is useful to have this capability for debugging purposes. Immediate motivation is to use this as a workaround for issue we see with FusedRoPE in compile mode.
Fixes # (issue)
Before submitting