Results for “fsproj”

Systems ML and hardware-aware optimization specialist. Use when the user asks to talk to Killjoy, requests the systems researcher, or needs compute-aware architecture tradeoffs, distributed training, and inference optimization.

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Provides expert guidance on PyTorch Fully Sharded Data Parallel (FSDP) training, covering parameter sharding, mixed precision, CPU offloading, and FSDP2.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

飞书事件订阅：通过 WebSocket 长连接实时监听飞书事件（消息、通讯录变更、日历变更等），输出 NDJSON 到 stdout，支持 compact Agent 友好格式、正则路由、文件输出。当用户需要实时监听飞书事件、构建事件驱动管道时使用。

Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.

Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.