ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
4,546 commits 391 branches 58 tags 304 MiB
Commit graph

2 commits

Author SHA1 Message Date
pre-commit-ci[bot]
4ddbb6ad80 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2026-03-12 23:10:59 +00:00
vivekkalyanarangan30
8c26ec2b0b Add multi-turn KV cache benchmark and model-specific integration tests 
- Add examples/kv_cache_multiturn_benchmark.py: realistic 15-turn tech
  support conversation (~1500 history tokens) with scaling test at 4, 8,
  12, and 16 messages to show speedup increasing with history length
- Add tests/test_past_kv_models.py: GPU integration tests for Llama,
  Qwen3, and Gemma2 past_key_values generation plus tuple-KV v5 compat
- Add tests/test_past_kv_utils.py: CPU-only unit tests for
  _ensure_cache_is_dynamic and _slice_position_ids utilities
 2026-03-12 23:10:59 +00:00