Zijie Tian 8fd25d72d7 Merge perf_opt-1 and perf_opt-2 branches ...

Combines two performance optimization features:
- perf_opt-1: Cross-layer pipeline for decode (double-buffered layer cache)
- perf_opt-2: Per-layer prefill buffer for async offload

Both features are complementary and improve CPU offload performance.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-07 06:03:44 +08:00

..

activation.py

fix

2025-06-15 13:28:29 +08:00

attention.py

Merge perf_opt-1 and perf_opt-2 branches

2026-01-07 06:03:44 +08:00

embed_head.py

simplify

2025-08-31 20:02:51 +08:00

layernorm.py

[refactor] Translate into english, void Chinese due to claude.

2025-12-11 00:30:24 +08:00

linear.py

simplify

2025-08-31 20:02:51 +08:00

rotary_embedding.py

simplify

2025-08-31 20:02:51 +08:00

sampler.py

[feat] Added bench_offload.py and GreedySampler.

2025-12-12 00:24:08 +08:00