Feat/streaming#45
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Streaming Classification for Decoder-KV Architecture
Adds incremental multi-session streaming classification to the GLiClass decoder-KV model.
New: gliclass/streaming/
Complete streaming pipeline with per-session KV cache management, batched multi-session processing, and pluggable classification trigger strategies. Six built-in strategies: EveryChunkStrategy, EveryNTokensStrategy, OnDelimiterStrategy, NeverStrategy, SlidingWindowStrategy, ComposedStrategy. Pipeline supports CPU offloading with pinned memory, async GPU transfers, sub-batch chunking, and explicit session management (delete_session, clear_sessions, active_sessions). Installable as pip install gliclass[streaming], does not affect the core package.
New: Decoder-KV architecture
GLiClassDecoderKV pairs a causal LM backbone Qwen3.0-Qwen3.5 support with DecoderKVScorer, a lightweight bidirectional DeBERTa-v2 encoder reading label hidden states at <>/<> positions.
Updated: gliclass/training.py
Added save_optimizer_state to TrainingArguments — skips saving optimizer and scheduler state in checkpoints to reduce checkpoint size on large models.