[Docs]: Add Release Documentation for Version 1.20.0 #501
+91
−9
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
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
abukhoy
requested review from
quic-rishinr,
ochougul,
quic-hemagnih and
quic-amitraj
as code owners
|
@quic-amitraj Check the latest github page: https://abukhoy.github.io/efficient-transformers/index.html |
abukhoy
commented
Jul 8, 2025
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
quic-hemagnih
requested changes
Jul 11, 2025
Signed-off-by: Abukhoyer Shaik <[email protected]>
quic-rishinr
requested changes
Jul 14, 2025
docs/source/validate.md
Outdated
|
|
||
| #### Single QPC | ||
|
|
||
| In the **Single QPC** setup, the entire model—including both image encoding and text generation—runs within a **single quantized configuration**. There is no model splitting, and all components operate within the same execution environment. |
There was a problem hiding this comment.
single quantized configuration? please rephrase this.
docs/source/release_docs.md
Outdated
| - **SpD & Multi-Projection Heads**: Token speculation via post-attention projections | ||
| - **I/O Encryption**: `--io-encrypt` flag support in compile/infer APIs | ||
| - **Separate Prefill/Decode Compilation**: For disaggregated serving | ||
| - **On-Device Sampling**: Reduces host-device latency for CausalLM models |
There was a problem hiding this comment.
its supported using vllm. Native Qeff doesnt support ondevice sampling please update the point accordingly
docs/source/release_docs.md
Outdated
| - Gradient checkpointing, device-aware `GradScaler`, and CLI `--help` added | ||
|
|
||
| --- | ||
| Thank you for using Efficient Transformers! For more details, refer to the full documentation. |
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
quic-rishinr
requested changes
Jul 14, 2025
docs/source/validate.md
Outdated
|
|
||
| **Single QPC:** | ||
| In the **Single QPC** setup, the entire model—including both image encoding and text generation—runs within a **single Qualcomm Program Container**. There is no model splitting, and all components operate within the same execution environment. | ||
| - The single QPC approach introduces the flexibility to run the vision and language components independently. |
There was a problem hiding this comment.
its not in single QPC we provide the flexibility to run the vision and language component independently. Its in the dual QPC approach.
in line 79 add single QPC (Qualcomm Program Container) instead of single Qualcomm Program Container
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Abukhoyer Shaik <[email protected]>
quic-rishinr
approved these changes
Jul 14, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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 introduces a new release documentation page (release_docs.md) for the Efficient Transformer library. The document outlines all the key updates included in Release 1.20.0, including:
✅ Newly onboarded models (e.g., Llama-4-Scout, Grok-1, Gemma3, Granite Vision/MOE)
✨ New features and enhancements (e.g., io_encrypt support, flexible pooling, on-device sampling)
🛠️ Fine-tuning support and improvements
🔮 Upcoming models and planned features for future releases
This documentation aims to provide a comprehensive overview of the current release for internal teams and external users.
Credit: @quic-amitraj