Remove gather scatter v0.14.0 #857
Closed
Conversation
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
Also overwrite qwen3_vl function to use _merge_multimodal_embeddings with index copy.
Format update
format
update for pre-commit error: vllm_gaudi/models/qwen3_vl.py:62:25: F821 Undefined name `_require_is_multimodal`
Signed-off-by: Libin Tang <litang@habana.ai>
Following reasoning stated in PR: vllm-project#616 Signed-off-by: Radoslaw Smyrek <radoslawx.smyrek@intel.com>
…ect#837) Signed-off-by: linoy buchnik <lbuchnik@habana.ai> Signed-off-by: Iryna Boiko <iboiko@habana.ai> Co-authored-by: Iryna Boiko <iboiko@habana.ai>
Adds support for cross-layer KV cache sharing on HPU, enabling models like Gemma-3n that share KV cache between layers to run on Gaudi. **Changes** - hpu_attn.py: Store kv_sharing_target_layer_name and skip KV cache writes for sharing layers - hpu_model_runner.py: Track shared layers, validate config, and set up tensor sharing during initialization - test_hpu_model_runner.py: Enable KV sharing unit tests **Expected Benefits** Reduced KV cache memory usage for models with layer sharing Lower TTFT for long-context scenarios in supported models (e.g., Gemma-3n) **Testing** Unit tests pass E2E validation with a KV-sharing model (e.g., Gemma-3n) pending --------- Signed-off-by: jakub-sochacki <jakub.sochacki@intel.com> Co-authored-by: jakub-sochacki <jakub.sochacki@intel.com>
Signed-off-by: Shiv Kaul <shiv.kaul@intel.com>
skaulintel
requested review from
adobrzyn,
afierka-intel,
iboiko-habana,
kamil-kaczor,
ksmusz,
kzawora-intel,
mgawarkiewicz-intel,
michalkuligowski and
xuechendi
as code owners
libinta
reviewed
Jan 21, 2026
| from vllm.v1.attention.backends.mla.common import MLACommonImpl | ||
| from vllm_gaudi.attention.ops.hpu_paged_attn import (HPUPagedAttention, HPUPagedAttentionMetadata, | ||
| HPUPagedAttentionMetadataBuilder) | ||
|
|
Contributor
There was a problem hiding this comment.
didn't change this file in original PR
libinta
reviewed
Jan 21, 2026
.github/CODEOWNERS
Outdated
| # See https://help.github.com/articles/about-codeowners/ | ||
| # for more info about CODEOWNERS file | ||
|
|
||
| * @kzawora-intel @xuechendi @adobrzyn @mgawarkiewicz-intel @afierka-intel @michalkuligowski @iboiko-habana @kamil-kaczor @ksmusz |
Contributor
There was a problem hiding this comment.
didn't change this file in original PR
libinta
reviewed
Jan 21, 2026
| query, key, value, attn_bias, 0.0, is_causal, scale, softmax_mode, recompute_mode, valid_seq_lengths, | ||
| padding_side | ||
| ] | ||
|
|
Contributor
There was a problem hiding this comment.
didnt chang this file in original PR
Contributor
Author
|
moved to #858 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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.
port #759 to v0.14.0 release