rustytorch

Author	SHA1	Message	Date
osobhandClaude Sonnet 5	4aaa36a57a	style: cargo fmt --workspace (whitespace/wrapping only, no semantic change) Whole-workspace rustfmt pass picked up while iterating on Mamba GPU backward work. Verified formatting-only via diff sampling; no logic changed. Co-Authored-By: Claude Sonnet 5 <[email protected]>	2026-08-10 07:09:36 -07:00
Omar SobhandClaude Sonnet 4.6	be3e3965b1	feat(batch10): attention sinks (StreamingLLM), chunked prefill, per-layer LR decay CI / Format Check (push) Failing after 26s Details CI / Build (ubuntu-latest) (push) Failing after 33s Details CI / Clippy Check (push) Failing after 34s Details CI / Build CPU-Only (Explicit) (push) Failing after 31s Details GPU Tests / Check GPU Availability (push) Successful in 0s Details GPU Tests / CUDA Tests (12.1) (push) Has been skipped Details Documentation / Build API Documentation (push) Failing after 30s Details Documentation / Build User Guide (push) Failing after 32s Details Performance Benchmarks / Run Benchmarks (push) Successful in 1m10s Details GPU Tests / CUDA Tests (11.8) (push) Has been skipped Details CI / Build (macos-latest) (push) Failing after 55s Details CI / Test (macos-latest) (push) Has been skipped Details CI / Test (ubuntu-latest) (push) Has been skipped Details CI / Python Bindings (maturin) (macos-latest) (push) Has been skipped Details CI / Python Bindings (maturin) (ubuntu-latest) (push) Has been skipped Details CI / WASM Build + Size Check (push) Has been skipped Details CI / Distributed Training Tests (push) Has been skipped Details CI / CI Success (push) Failing after 0s Details GPU Tests / Metal Tests (push) Has been skipped Details - Attention sinks (arXiv:2309.17453): AttentionSinkEviction always retains first sink_size KV positions + last window_size; evicts middle band in O(evict_count); select_evict_positions/should_retain consistent; 15 tests - Chunked prefill (vLLM arXiv:2309.06180): ChunkedPrefillScheduler splits long prompts into chunk_size=512 chunks interleaved with decode steps (max 128 decode tokens/step); PrefillChunkState tracks progress/remaining/completion; drain_completed(); 14 tests including 1500-token→3-chunk coverage - Per-layer LR decay (ULMFiT / discriminative fine-tuning): LayerLrDecayConfig with base_lr * decay_rate^(num_layers-1-depth); LayerLrDecayBuilder parses layer/layers/ h/blocks/bracket notation param names; LayerLrScheduler with outer multiplier for cosine/linear schedule composition; 14 tests + 1 doctest Co-Authored-By: Claude Sonnet 4.6 <[email protected]>	2026-06-27 04:53:53 +00:00