Open Source Projects By SemiAnalysis in collaboration with the community. InferenceX™, Assembly ISA level microbenchmarking, AMDGPU LLVM & NVIDIA ptxas Compiler Fuzzing
由 SemiAnalysis 与社区合作打造的开源项目。InferenceX™、汇编 ISA 级微基准测试、AMDGPU LLVM 与 NVIDIA ptxas 编译器模糊测试
AgentX Harness - Realistic 1mil Long Context, Multi Turn Agentic Workload Trace Replayer, collected from over $3mil USD of Traces | AgentX Harness—真实百万级长上下文、多轮 Agentic 工作负载轨迹回放器，采集自价值超 300 万美元的真实调用轨迹
tooling to support clustermax.ai, the industry standard rating system for neoclouds
GRPO on MiMo coding tasks: Qwen3.6-35B full-param RL via Fireworks Dedicated Training API, Harbor rollouts, E2B sandboxes (pre-release, to be open-sourced)
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
A simple, fast and robust program-aware agentic inference system.
Loading…