Add Qwen3.5/3.6 model families#1514
Open
YunchaoYang wants to merge 4 commits into
Open
Conversation
added 2 commits
May 27, 2026 20:45
Implement the Qwen 3.5 model family in fairseq2 with hybrid GatedDeltaNet linear attention (75%) + full attention (25%) architecture. Includes: - GatedDeltaNet module with chunked/recurrent delta rule kernels, causal conv1d, and fused PyTorch fallbacks - Qwen35Attention with partial RoPE, QK-norm, and output gating - Qwen35DecoderLayer supporting both full and linear attention types - Top-K MoE routing with shared experts for MoE variants - Bidirectional HuggingFace state dict conversion with RMSNorm 1+w convention handling - Asset cards for all model sizes (0.8B, 2B, 9B, 27B, MoE 35B-A3B) - 42 unit tests covering all modules and interop - Integration test for HF logit parity (Qwen3.5-0.8B) - SFT and pretraining recipe configs
YunchaoYang
requested review from
MartinGleize,
cbalioglu and
zyaoj
as code owners
meta-cla
Bot
added
the
CLA Signed
added 2 commits
May 27, 2026 20:57
Merge 5 separate test files (test_gated_delta_net, test_qwen35_attention, test_qwen35_decoder_layer, test_qwen35_interop, test_qwen35_moe) into one test_qwen35.py with 19 focused tests covering all modules.
YunchaoYang
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do? Please describe:
A summary of the change or the issue that is fixed.
Fixes #{issue number}
Does your PR introduce any breaking changes? If yes, please list them:
List of all backwards-incompatible changes.
Check list: