Brandon M. Music
@brandonmmusic-maxI am practicing lawyer from Kentucky who took an interest in ai systems engineering. I've been coding in some form for 30 years .
Language Breakdown
Lines of code distribution across 6 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in Cuda
Collaboration Network
Global Impact visualization
Repos
12
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Yuanhang Sun
@leavelet
Matthew Bonanni
@MatthewBonanni
Luke Alonso
@lukealonso
RobTand
@RobTand
Ka-Hyun Nam
@kahyunnam
Top Repositories
SM120 Kernels
Qwen3.5-397B-NVFP4 production SGLang stack on 4× RTX PRO 6000 Blackwell (SM120 PCIe) — 204 tok/s single-user, 563 tok/s peak aggregate
Neuron-centric fused MoE kernel for SM120 NVFP4 — 17.5μs/layer, 1.02x faster than VerdictMoE, 5.6x faster than CUTLASS
The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.
Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
DFlash: Block Diffusion for Flash Speculative Decoding
CUDA Templates and Python DSLs for High-Performance Linear Algebra
A high-throughput and memory-efficient inference and serving engine for LLMs
FlashInfer: Kernel Library for LLM Serving
Open Source Impact
Contributions to external projects
