[Docs]: release/v1.21.6 doc update#1007
Open
abukhoy wants to merge 1 commit into
Open
Conversation
Signed-off-by: Abukhoyer Shaik <abukhoye@qti.qualcomm.com>
quic-hemagnih
requested changes
May 25, 2026
| # Efficient Transformer Library - 1.21.6 Release Notes | ||
|
|
||
| Welcome to the official release of **Efficient Transformer Library v1.21.6**! This targeted release builds on the v1.21 line with multi-resolution Vision Language Model workflows, Qwen3-VL stability fixes, on-device sampling enablement, and compatibility updates for newer model and framework APIs. | ||
|
|
Contributor
There was a problem hiding this comment.
Also add online serving support for Gemma4 through vLLM
| ## Key Features & Enhancements | ||
|
|
||
| - **Multi-specialization vision compilation for Qwen VLMs** | ||
| - Qwen2.5-VL, Qwen3-VL Dense, and Qwen3-VL-MoE can compile multiple vision resolution and frame configurations in one pass. |
Contributor
There was a problem hiding this comment.
WE should remove QWE3-VL MOE model from this list, as this model is not tested by SIT in this release. We should only keep the models which are vetted by SIT.
| - Qwen2.5-VL, Qwen3-VL Dense, and Qwen3-VL-MoE can compile multiple vision resolution and frame configurations in one pass. | ||
| - `height`, `width`, and `num_frames` can be supplied as lists when building specializations. | ||
| - Runtime generation can select the matching specialization through the multi-frame generation path. | ||
| - New example scripts are available for [Qwen2.5-VL](https://github.com/quic/efficient-transformers/tree/release/v1.21.6/examples/image_text_to_text/models/qwen2_5_vl), [Qwen3-VL Dense](https://github.com/quic/efficient-transformers/tree/release/v1.21.6/examples/image_text_to_text/models/qwen3vl), and [Qwen3-VL-MoE](https://github.com/quic/efficient-transformers/tree/release/v1.21.6/examples/image_text_to_text/models/qwen3_vl_moe). |
Contributor
There was a problem hiding this comment.
remove qwen3-vl moe example script also. Only keep Qwen2.5VL and QWEN3-VL dense models
| - Adds regression coverage for large embedding and reranker model export flows. | ||
|
|
||
| - **Qwen VLM runtime stability** | ||
| - Fixes RoPE handling for Qwen3-VL-MoE disaggregated mode. |
|
|
||
| - **Gemma3 configuration compatibility** | ||
| - Updates Gemma3 cache handling for the newer `_sliding_window_pattern` config field. | ||
| - Preserves sliding-window behavior for Gemma3 models using updated Transformers configs. |
Contributor
There was a problem hiding this comment.
add online serving support for Gemma3 through vLLM is added
| - Accepts `vision_feature_layer` and `vision_feature_select_strategy` forwarded by newer Transformers Llama4 APIs. | ||
| - Fixes ONNX export failures for Llama4 vision models while remaining backward compatible. | ||
|
|
||
| --- |
Contributor
There was a problem hiding this comment.
Add GPT OSS 120B with BS>1 and GPT OSS 20B BS>2 support is enabled
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.
This Pr is created for updating the release docs of the release branch
release/v1.21.6.