8000 Tom-CaoZH (Zhang Cao) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View Tom-CaoZH's full-sized avatar
👋
Focusing
👋
Focusing

Highlights

  • Pro

Block or report Tom-CaoZH

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

Disaggregated Prefill-Decode LLM serving engine on mini-sglang with a proved KV page state machine (PdLedger)

TLA 25 1 Updated Nov 11, 2026

Formal verification workflow and skill stack for coding agents (TLA+, Z3, Apalache, TLAPS)

Python 89 6 Updated Nov 20, 2026

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Python 26,297 3,244 Updated Nov 19, 2026
Lean 17,636 2,001 Updated Oct 30, 2026

An open, visual atlas of looped transformers, recurrent computation, adaptive depth, and latent reasoning.

CSS 41 4 Updated Oct 28, 2026

Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.

Python 1,611 140 Updated Oct 19, 2026

SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses

TypeScript 3,693 303 Updated Nov 21, 2026

DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers

Cuda 550 81 Updated Sep 30, 2026

A lightweight library for xPU kernel JIT compilation

C++ 475 80 Updated Nov 19, 2026

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Python 4,835 377 Updated Jan 14, 2026

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

147 11 Updated Mar 14, 2026

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

Python 17,572 1,746 Updated Nov 21, 2026

Dynamic Memory Management for Serving LLMs without PagedAttention

C 527 47 Updated Aug 24, 2026

Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.

Python 269 71 Updated Oct 6, 2026

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Python 1,218 97 Updated Nov 21, 2026

Closed-loop fault localization and checkpoint recovery for LLM Pre-training

Python 190 10 Updated Nov 16, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 285,072 35,438 Updated Nov 18, 2026
Go 98 9 Updated Sep 15, 2025

AgentENV (AENV) is a distributed platform for running agent environments at scale.

Rust 3,775 375 Updated Nov 20, 2026

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

Python 1,216 153 Updated Oct 12, 2026

Open Frontier Intelligence

9,109 796 Updated Aug 6, 2026

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST.…

C++ 818 110 Updated Nov 20, 2026

Production-ready MoE load balancing via real-time expert replication

Cuda 266 21 Updated Oct 15, 2026

Language model tokenization at GB/s

Rust 4,156 226 Updated Nov 2, 2026

A distributed framework for LLM agents

Python 608 26 Updated Nov 3, 2026

Scalable RL for Any Agent and Sandbox.

Python 822 102 Updated Aug 27, 2026

JetSpec++/JetSpec: Causal Parallel (Tree) Drafting with Self Refinement

Python 262 16 Updated Nov 18, 2026

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Python 7,324 703 Updated Jul 9, 2026

Block-GTQ: RoPE-aware bit allocation for KV-cache quantization

Python 17 1 Updated Oct 29, 2026
Next
0