mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
LLMLingua was the original ML text compressor (BERT-based). Kompress (ModernBERT, trained on 330K structured tool outputs) replaced it with better compression quality and simpler architecture. Removed across 35 files: - Deleted headroom/transforms/llmlingua_compressor.py - Deleted tests/test_transforms/test_llmlingua_compressor.py - Deleted tests/test_proxy_llmlingua.py - Removed all enable_llmlingua config, _get_llmlingua methods, LLMLingua fallback paths, LLMLINGUA strategy enum values - Removed CLI flags, model configs, compression handler references - Simplified ContentRouter: Kompress is primary and only text compressor |
||
|---|---|---|
| .. | ||
| scenarios | ||
| __init__.py | ||
| adversarial_ccr_tests.py | ||
| agent_cost_benchmark.py | ||
| bench_latency.py | ||
| bench_relevance.py | ||
| bench_transforms.py | ||
| ccr_regression_benchmark.py | ||
| comprehensive_eval.py | ||
| compression_benchmark.py | ||
| conftest.py | ||
| dynamic_detector_benchmark.py | ||
| headroom_adversarial_benchmark.py | ||
| headroom_worst_case_benchmark.py | ||
| prefix_cache_benchmark.py | ||
| real_world_agent_benchmark.py | ||
| run_benchmarks.py | ||