Cherry-picks to enable Llama4 Maverick#882
Merged
wpyszka merged 4 commits intoJan 28, 2026
Merged
Conversation
Contributor
rsmyrek
commented
Jan 26, 2026
rsmyrek
commented
- Interleaved sliding window fix #805
- [GAUDISW-245665] fix diverge from vllm in multiModalBudget #837
- Fix Llama4 shape mismatch for 32k+ context window (#842) #855
- Flatten positions only when QK norm is enabled #862
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>
…llm-project#855) Llama4 for `max_model_len > 32k` enable temperature adjustment https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/llama4.py#L719. Enabled adjustment causes tensor `q` shape modification from 2D to 3D: https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/llama4.py#L307. This tensor is passing to `UnqnatizedFusedMoEMetod -> forward`: https://github.com/vllm-project/vllm-gaudi/blob/main/vllm_gaudi/ops/hpu_fused_moe.py#L163 causing invalid reshaping - we trying to return a 3D `output.view` based on 2D output tensor. Found that following PR introduced the bug: vllm-project#680 and vllm-project#684 Cherry-picked from `releases/v0.13.0` --------- Signed-off-by: Artur Fierka <artur.fierka@intel.com>
Signed-off-by: Radoslaw Smyrek <radoslawx.smyrek@intel.com>
🚧 CI BlockedThe main CI workflow was not started for the following reason:
|
rsmyrek
requested review from
mgawarkiewicz-intel,
piotrbocian and
wpyszka
as code owners
✅ CI PassedAll checks passed successfully against the following vllm commit: |
jkaniecki
approved these changes
Jan 27, 2026
wpyszka
requested review from
adobrzyn,
afierka-intel,
iboiko-habana and
michalkuligowski
adobrzyn
approved these changes
Jan 28, 2026
wpyszka
merged commit 9ab497d
into
vllm-project:releases/v0.14.1
64 of 65 checks passed
wpyszka
pushed a commit
that referenced
this pull request
Jan 29, 2026
Reverts part of: #882 Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
slokesha
pushed a commit
to libinta/vllm-gaudi
that referenced
this pull request
Jan 29, 2026
1. vllm-project#805 2. vllm-project#837 3. vllm-project#855 4. vllm-project#862 --------- Signed-off-by: Radoslaw Smyrek <radoslawx.smyrek@intel.com> Signed-off-by: linoy buchnik <lbuchnik@habana.ai> Signed-off-by: Iryna Boiko <iboiko@habana.ai> Signed-off-by: Artur Fierka <artur.fierka@intel.com> Co-authored-by: Linoy Buchnik <linoybu@gmail.com> Co-authored-by: Iryna Boiko <iboiko@habana.ai> Co-authored-by: Artur Fierka <artur.fierka@intel.com> Signed-off-by: slokesha <slokeshappa@habana.ai>
slokesha
pushed a commit
to libinta/vllm-gaudi
that referenced
this pull request
Jan 29, 2026
Reverts part of: vllm-project#882 Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai> Signed-off-by: slokesha <slokeshappa@habana.ai>
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
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.