Repository navigation
Conversation
This was referenced Nov 7, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add LightLLM support for Qwen3.8 Flash Next, including the Qwen4-Exp model path, gated residual and n-gram embedding components, QSA kernels, pinned/row-sharded embeddings, multimodal handling, request-slot accounting, and focused regression coverage.
This branch is based directly on
upstream/mainand keeps the feature plus its formatter cleanup in a minimal two-commit history.Validation
python -m compileall -q lightllm unit_tests testgit diff --checkpre-commit run --files <all changed files>(Black and Flake8)pytest -q unit_tests/models/qwen4_exp/test_batch.py unit_tests/models/qwen4_exp/test_lexical_cache.py unit_tests/models/qwen4_exp/test_attention_state.py unit_tests/common/ngram_embedding/test_hash.py unit_tests/common/qsa/test_topk_compatibility.py(74 passed)GPU model execution and H100 benchmark claims require the corresponding CUDA/dependency environment and are not asserted by this local validation.