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	0e1d6a74b6	feat(batch6): windowed acceptance metrics, KV INT8 quant, col/row-parallel linear CI / Format Check (push) Failing after 6s Details GPU Tests / Check GPU Availability (push) Successful in 0s Details CI / Clippy Check (push) Failing after 8s Details Documentation / Build User Guide (push) Successful in 8s Details Documentation / Build API Documentation (push) Failing after 19s Details CI / Build (ubuntu-latest) (push) Failing after 53s Details Performance Benchmarks / Run Benchmarks (push) Successful in 7m57s Details GPU Tests / CUDA Tests (11.8) (push) Has been skipped Details GPU Tests / CUDA Tests (12.1) (push) Has been skipped Details CI / Build CPU-Only (Explicit) (push) Failing after 1m6s Details CI / CI Success (push) Failing after 0s Details CI / Build (macos-latest) (push) Failing after 28s 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 GPU Tests / Metal Tests (push) Has been skipped Details Windowed acceptance rate (rtx-inference/speculative): - WindowedAcceptanceTracker: O(1) VecDeque sliding window, p50/p95/min/max - AcceptanceTrend enum (Rising/Falling/Stable, ±0.05 threshold) - AcceptanceDashboard aggregator; wired into PerformanceMetrics::update() and dashboard(); 13 tests KV cache INT8 quantization (rtx-inference/cache): - KvCacheQuantMode { None, Int8 { scale_per_token }, Fp8E4M3 } enum - KvQuantizer::encode/decode: symmetric per-block INT8 (scale=max_abs/127) gives 4× compression vs f32; Fp8E4M3 CPU proxy, GPU path reserved - QuantizedKvBlock carries data+scale+mode; KvCacheConfig::quant_mode defaulting to None; 14 tests ColParallel + RowParallel linear (rtx-distributed): - ColParallelLinear: shards weight rows across TP ranks, forward_cpu() batch matmul + per-shard bias; no AllReduce (output shards concatenated) - RowParallelLinear: shards weight cols across TP ranks, forward_cpu() partial sum + bias on rank 0 only; async forward() calls ProcessGroup AllReduce for real NCCL path; CPU sim is no-op - TensorParallel::matmul() replaced zeros stub with ColParallelLinear(tp=1) - col→row roundtrip verified within 1e-3; 9 tests Co-Authored-By: Claude Sonnet 4.6 <[email protected]>	2026-06-27 03:54:07 +00:00
redclawsystems	4d88dc0584	Initial commit	2026-03-04 00:08:42 +00:00