Ml Performance Reading Group Session

June 12, 2026
Media Summary: Presenter: Daniel Vega-Myhre, with part by wave_function Paper: Paper: LMCache ( Presenter: A. Mahmood Slides: ...

Ml Performance Reading Group Session - Detailed Analysis & Overview

Presenter: Daniel Vega-Myhre, with part by wave_function Paper: Paper: LMCache ( Presenter: A. Mahmood Slides: ...

Photo Gallery

ML Performance Reading Group Session 19: Speculative Decoding
ML Performance Reading Group Session 24: Flash Attention 4
ML Performance Reading Group Session 1: GPU Architecture, CUDA, NCCL
ML Performance Reading Group Session 2: Flash Attention
ML Performance Reading Group Session 18: Kimi Delta Attention
ML Performance Reading Group Session 16: LMCache
ML Performance Reading Group Session 15: Megablocks
ML Performance Reading Group Session 5: Paged Attention
ML Performance Reading Group Session 17: MXFP8 Training for MoEs with TorchAO
ML Performance Reading Group Session 25: Prefill as a Service
ML Performance Reading Group Session 6: Zero Bubble Pipeline Parallelism
ML Performance Reading Group Session 11: Async Tensor Parallelism

Related Security Resources

ML Performance Reading Group Session 19: Speculative Decoding ML Performance Reading Group Session 24: Flash Attention 4 ML Performance Reading Group Session 1: GPU Architecture, CUDA, NCCL ML Performance Reading Group Session 2: Flash Attention ML Performance Reading Group Session 18: Kimi Delta Attention ML Performance Reading Group Session 16: LMCache ML Performance Reading Group Session 15: Megablocks ML Performance Reading Group Session 5: Paged Attention The Surprising Truth Behind Behr's Most Popular Deck Stain Colors: Trends And Fads The Hidden Parenting Struggle Behind 'Amelie': Expert Tips For Realistic Expectations Chase Iban Alert: Are You At Risk Of Losing Your Account Access Garden Grove Evacuates Under Orange Alert What Residents Need To Know The Obituaries Trend Nobody Talks About In Elkin, NC: How Johnson Funeral Home's Listings Expose Hidden Aspects Of Local Lives The Hidden Risk Of Using An Outdated Hawaiian Airlines Mastercard Login ATK Hairry: The Dark Horse Of Hair Care That's Gaining Momentum Fast PST Or BST? The Hidden Consequences Of Not Making This One Simple Switch
View Detailed Profile
ML Performance Reading Group Session 19: Speculative Decoding

ML Performance Reading Group Session 19: Speculative Decoding

Session

ML Performance Reading Group Session 24: Flash Attention 4

ML Performance Reading Group Session 24: Flash Attention 4

ML Performance Reading Group Session

ML Performance Reading Group Session 1: GPU Architecture, CUDA, NCCL

ML Performance Reading Group Session 1: GPU Architecture, CUDA, NCCL

ML Performance

ML Performance Reading Group Session 2: Flash Attention

ML Performance Reading Group Session 2: Flash Attention

ML Performance Reading Group Session

ML Performance Reading Group Session 18: Kimi Delta Attention

ML Performance Reading Group Session 18: Kimi Delta Attention

Presenter: Daniel Vega-Myhre, with part by wave_function Paper: https://arxiv.org/pdf/2510.26692.

ML Performance Reading Group Session 16: LMCache

ML Performance Reading Group Session 16: LMCache

Paper: LMCache (https://arxiv.org/pdf/2510.09665) Presenter: A. Mahmood Slides: ...

ML Performance Reading Group Session 15: Megablocks

ML Performance Reading Group Session 15: Megablocks

Paper: Megablocks (https://arxiv.org/pdf/2211.15841) Presenter: rdyro.

ML Performance Reading Group Session 5: Paged Attention

ML Performance Reading Group Session 5: Paged Attention

ML Performance Reading Group Session

ML Performance Reading Group Session 17: MXFP8 Training for MoEs with TorchAO

ML Performance Reading Group Session 17: MXFP8 Training for MoEs with TorchAO

Presenter: Daniel Vega-Myhre Code: https://github.com/pytorch/ao/tree/main/torchao/prototype/moe_training.

ML Performance Reading Group Session 25: Prefill as a Service

ML Performance Reading Group Session 25: Prefill as a Service

Paper: https://www.alphaxiv.org/abs/2604.15039v1 Slides: ...

ML Performance Reading Group Session 6: Zero Bubble Pipeline Parallelism

ML Performance Reading Group Session 6: Zero Bubble Pipeline Parallelism

ML Performance Reading Group Session

ML Performance Reading Group Session 11: Async Tensor Parallelism

ML Performance Reading Group Session 11: Async Tensor Parallelism

ML Performance Reading Group Session

ML Performance Reading Group Session 8: Megatron-LM

ML Performance Reading Group Session 8: Megatron-LM

ML Performance Reading Group Session