[SW-185803] Enable FusedSDPA fp8 in Llama FT#310
Merged
Conversation
pbielak
requested review from
bhargaveede,
libinta,
mandy-li,
ssarkar2 and
vivekgoe
as code owners
pbielak
requested review from
MrGeva,
guyeilat,
oabramovich and
scsudhak-intel
and removed request for
a user,
libinta,
mandy-li and
ssarkar2
vivekgoe
suggested changes
Jul 29, 2024
vivekgoe
left a comment
vivekgoe
left a comment
There was a problem hiding this comment.
@pbielak @wszczurekhabana added a few comments, please check.
vivekgoe
reviewed
Jul 30, 2024
|
@pbielak Thanks for updates. Please check my latest responses. Please also resolve conflicts in modeling_llama.py. |
pbielak
force-pushed
the
dev/pbielak/enable-fusedSDPA-fp8
branch
4 times, most recently
from
41f8967 to
c77f6fb
Compare
- Update attention module and usages - Add --flash_attention_fp8 flag - Fix failure in distributed text-generation - Add assert for Gaudi 3 - Remove unnecessary repeat_kv and reshape - Rename FusedAttention to FusedAttentionTE - Move flash_attention_fp8 checks - Fix fused_scaled_dot_product_attention calls
pbielak
force-pushed
the
dev/pbielak/enable-fusedSDPA-fp8
branch
from
c77f6fb to
19384dd
Compare
vivekgoe
approved these changes
Aug 1, 2024
astachowiczhabana
pushed a commit
that referenced
this pull request
Aug 6, 2024
- Update attention module and usages - Add --flash_attention_fp8 flag - Fix failure in distributed text-generation - Add assert for Gaudi 3 - Remove unnecessary repeat_kv and reshape - Rename FusedAttention to FusedAttentionTE - Move flash_attention_fp8 checks - Fix fused_scaled_dot_product_attention calls Change-Id: Ica468bb23931a78e2a23f6cb9bc60f87dd442007
astachowiczhabana
pushed a commit
that referenced
this pull request
Aug 6, 2024
- Update attention module and usages - Add --flash_attention_fp8 flag - Fix failure in distributed text-generation - Add assert for Gaudi 3 - Remove unnecessary repeat_kv and reshape - Rename FusedAttention to FusedAttentionTE - Move flash_attention_fp8 checks - Fix fused_scaled_dot_product_attention calls Change-Id: Ica468bb23931a78e2a23f6cb9bc60f87dd442007
astachowiczhabana
pushed a commit
that referenced
this pull request
Aug 7, 2024
- Update attention module and usages - Add --flash_attention_fp8 flag - Fix failure in distributed text-generation - Add assert for Gaudi 3 - Remove unnecessary repeat_kv and reshape - Rename FusedAttention to FusedAttentionTE - Move flash_attention_fp8 checks - Fix fused_scaled_dot_product_attention calls Change-Id: Ica468bb23931a78e2a23f6cb9bc60f87dd442007
pbielak
pushed a commit
that referenced
this pull request
Oct 1, 2024
astachowiczhabana
pushed a commit
that referenced
this pull request
Oct 9, 2024
- Update attention module and usages - Add --flash_attention_fp8 flag - Fix failure in distributed text-generation - Add assert for Gaudi 3 - Remove unnecessary repeat_kv and reshape - Rename FusedAttention to FusedAttentionTE - Move flash_attention_fp8 checks - Fix fused_scaled_dot_product_attention calls Change-Id: Ica468bb23931a78e2a23f6cb9bc60f87dd442007
xinyu-intel
pushed a commit
that referenced
this pull request
Mar 4, 2025
- Update attention module and usages - Add --flash_attention_fp8 flag - Fix failure in distributed text-generation - Add assert for Gaudi 3 - Remove unnecessary repeat_kv and reshape - Rename FusedAttention to FusedAttentionTE - Move flash_attention_fp8 checks - Fix fused_scaled_dot_product_attention calls Change-Id: Ica468bb23931a78e2a23f6cb9bc60f87dd442007
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.
Same PR as in #291, but I fixed the error occurring in the
text-generation/run_lm_eval.pyscript by moving one import from top-level to function-level, i.e., see 3af45d2