back
user profile

matt_d

21,167karma·3,275submissions·April 21, 2014
recent activity (3,275 total)
2 pts
Dynamic Persistent Tile Scheduling w/ Cluster Launch Control (CLC) on Blackwell(research.colfax-intl.com)
3mo ago·discuss
2 pts
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?(github.com)
3mo ago·discuss
3 pts
CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure(arxiv.org)
3mo ago·discuss
1 pts
Microbenchmark-Driven Analytical Performance Modeling Across Modern GPUs(arxiv.org)
3mo ago·discuss
2 pts
PyTorch DevLog(docs.pytorch.org)
3mo ago·discuss
2 pts
VDCores: Resource Decoupled Programming and Execution for Asynchronous GPU(arxiv.org)
3mo ago·discuss
1 pts
Aurora: A Leverage-Aware Optimizer for Rectangular Matrices(blog.tilderesearch.com)
3mo ago·discuss
1 pts
The Two Abstractions of System Design: Hide or Reduce(muratbuffalo.blogspot.com)
3mo ago·discuss
2 pts
Practical Formal Verification for MLIR Programs(arxiv.org)
3mo ago·discuss
2 pts
Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs(arxiv.org)
3mo ago·discuss
3 pts
Capsules: Compile-time lock discipline in OxCaml(kcsrk.info)
3mo ago·discuss
2 pts
Data Race Freedom in OxCaml(kcsrk.info)
3mo ago·discuss
3 pts
cuda-oxide: a custom rustc backend for compiling GPU kernels in pure Rust(github.com)
3mo ago·discuss
3 pts
A case study with Aeneas and jxl-rs(jonathan.protzenko.fr)
3mo ago·discuss
3 pts
Finite Functional Programming(arxiv.org)
3mo ago·discuss
5 pts
CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion(arxiv.org)
3mo ago·discuss
3 pts
SPEC CPU: The Next Generation(arxiv.org)
3mo ago·discuss
2 pts
Persistent Iterators with Value Semantics(arxiv.org)
3mo ago·discuss
3 pts
Continual Learning Bench 1.0(continual-learning-bench.com)
3mo ago·discuss
6 pts
The Valley of Calm(blog.joemag.dev)
3mo ago·discuss
2 pts
The Static Dynamic JVM – A Many Layered Dive [video](youtube.com)
3mo ago·1 comments
2 pts
Learning Randomized Reductions(arxiv.org)
3mo ago·discuss
3 pts
Metastability in Recovery: Cascading Recovery with a Loop(charap.co)
3mo ago·discuss
4 pts
How the JVM Optimizes Generic Code – A Deep Dive(inside.java)
3mo ago·discuss
1 pts
Tessera: Unlocking Heterogeneous GPUs Through Kernel-Granularity Disaggregation(arxiv.org)
3mo ago·discuss
comment
Blog post: https://www.rabdos.ai/research/introducing-mathduels-ai Leaderboard: https://mathduels.ai/ …
3mo ago·view thread
2 pts
MathDuels: Evaluating LLMs as Problem Posers and Solvers(arxiv.org)
3mo ago·1 comments
1 pts
Kernel Contracts: A Spec. Language for Correctness Across Heterogeneous Silicon(arxiv.org)
3mo ago·discuss
2 pts
Revealing NVIDIA Driver Command Streams for CPU-GPU Runtime Behavior Insight(arxiv.org)
3mo ago·discuss
2 pts
Guardians: Static verification for AI agent workflows(github.com)
3mo ago·discuss