2.0 -//Pentabarf//Schedule 1.0//EN

Schedule for sessions at

PUBLISH 9808@fosdem-2026@pentabarf.org

9808

Q3M37H-welcome_to_the_ai_plumbers_devroom

Welcome to the AI Plumbers Devroom en

en_US

AI Plumbers 2026-01-31 10:30:00 +0100 2026-01-31 10:35:00 +0100 00:05:00:00 20260131T103000 20260131T103500 00:05:00:00

Welcome to the AI Plumbers Devroom-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/Q3M37H-welcome_to_the_ai_plumbers_devroom/ UD2.120 (Chavanne) Roman Shaposhnik Tanya Dadasheva PUBLISH 8429@fosdem-2026@pentabarf.org

8429

LRZJEH-llama-cpp-multimodal

Multimodal support in llama.cpp - Achievements and Future Directions en

en_US

AI Plumbers 2026-01-31 10:35:00 +0100 2026-01-31 10:55:00 +0100 00:20:00:00 20260131T103500 20260131T105500 00:20:00:00

Multimodal support in llama.cpp - Achievements and Future Directions-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/LRZJEH-llama-cpp-multimodal/ UD2.120 (Chavanne) Xuan-Son Nguyen PUBLISH 9120@fosdem-2026@pentabarf.org

9120

C9NF8K-api_remoting_for_llama_cpp_near-native_gpu_speed_in_macos_containers

API Remoting for llama.cpp: Near-Native GPU Speed in macOS Containers en

en_US

AI Plumbers 2026-01-31 11:00:00 +0100 2026-01-31 11:20:00 +0100 00:20:00:00 20260131T110000 20260131T112000 00:20:00:00

API Remoting for llama.cpp: Near-Native GPU Speed in macOS Containers-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/C9NF8K-api_remoting_for_llama_cpp_near-native_gpu_speed_in_macos_containers/ UD2.120 (Chavanne) José Castillo Lema PUBLISH 8706@fosdem-2026@pentabarf.org

8706

YJJQTD-tract-and-torch-to-nnef

tract - an efficient rust neural network inference engine en

en_US

AI Plumbers 2026-01-31 11:25:00 +0100 2026-01-31 11:45:00 +0100 00:20:00:00 20260131T112500 20260131T114500 00:20:00:00

tract - an efficient rust neural network inference engine-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/YJJQTD-tract-and-torch-to-nnef/ UD2.120 (Chavanne) Julien Balian Mathieu Poumeyrol PUBLISH 9366@fosdem-2026@pentabarf.org

9366

X9XTL3-mliot

Beyond TinyML: Balance inference accuracy and latency on MCUs en

en_US

AI Plumbers 2026-01-31 11:50:00 +0100 2026-01-31 12:10:00 +0100 00:20:00:00 20260131T115000 20260131T121000 00:20:00:00

Beyond TinyML: Balance inference accuracy and latency on MCUs-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/X9XTL3-mliot/ UD2.120 (Chavanne) Charalampos Mainas Anastassios Nanos Anastasia Mallikopoulou PUBLISH 8633@fosdem-2026@pentabarf.org

8633

Z3TEMS-executorch-for-bare-metal-microcontrollers

Bringing up bare metal ExecuTorch on RISC-V en

en_US

AI Plumbers 2026-01-31 12:15:00 +0100 2026-01-31 12:35:00 +0100 00:20:00:00 20260131T121500 20260131T123500 00:20:00:00

Bringing up bare metal ExecuTorch on RISC-V-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/Z3TEMS-executorch-for-bare-metal-microcontrollers/ UD2.120 (Chavanne) William Jones Jeremy Bennett Shane Slattery Pietra Ferreira PUBLISH 8384@fosdem-2026@pentabarf.org

8384

E7WQQX-webnn_and_webllm_on_risc-v_closing_the_ai_acceleration_gap_with_rvv_and_tenstorr

WebNN and WebLLM on RISC-V: Closing the AI Acceleration Gap with RVV and Tenstorrent en

en_US

AI Plumbers 2026-01-31 12:40:00 +0100 2026-01-31 13:00:00 +0100 00:20:00:00 20260131T124000 20260131T130000 00:20:00:00

WebNN and WebLLM on RISC-V: Closing the AI Acceleration Gap with RVV and Tenstorrent-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/E7WQQX-webnn_and_webllm_on_risc-v_closing_the_ai_acceleration_gap_with_rvv_and_tenstorr/ UD2.120 (Chavanne) Yuning Liang Petr Penzin PUBLISH 8184@fosdem-2026@pentabarf.org

8184

QU9UF3-slang-cross-platform-inference

Single-source cross-platform GPU LLM inference with Slang and Rust en

en_US

AI Plumbers 2026-01-31 13:05:00 +0100 2026-01-31 13:25:00 +0100 00:20:00:00 20260131T130500 20260131T132500 00:20:00:00

Single-source cross-platform GPU LLM inference with Slang and Rust-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/QU9UF3-slang-cross-platform-inference/ UD2.120 (Chavanne) Crozet Sébastien PUBLISH 9546@fosdem-2026@pentabarf.org

9546

DKKE8W-self-learning-compiler-docc

Closing the Loop: A Self-Learning Compiler for AI Accelerators en

en_US

AI Plumbers 2026-01-31 13:30:00 +0100 2026-01-31 13:50:00 +0100 00:20:00:00 20260131T133000 20260131T135000 00:20:00:00

Closing the Loop: A Self-Learning Compiler for AI Accelerators-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/DKKE8W-self-learning-compiler-docc/ UD2.120 (Chavanne) Ramon Wirsch PUBLISH 9167@fosdem-2026@pentabarf.org

9167

B39JSW-one-gpu-many-models

One GPU, Many Models: What Works and What Segfaults en

en_US

AI Plumbers 2026-01-31 13:55:00 +0100 2026-01-31 14:15:00 +0100 00:20:00:00 20260131T135500 20260131T141500 00:20:00:00

One GPU, Many Models: What Works and What Segfaults-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/B39JSW-one-gpu-many-models/ UD2.120 (Chavanne) YASH PANCHAL PUBLISH 9150@fosdem-2026@pentabarf.org

9150

7PAYWS-oneai_an_open-source_framework_for_managing_ai_models_at_scale

OneAI: An Open-Source Framework for Managing AI Models at Scale en

en_US

AI Plumbers 2026-01-31 14:20:00 +0100 2026-01-31 14:40:00 +0100 00:20:00:00 20260131T142000 20260131T144000 00:20:00:00

OneAI: An Open-Source Framework for Managing AI Models at Scale-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/7PAYWS-oneai_an_open-source_framework_for_managing_ai_models_at_scale/ UD2.120 (Chavanne) Daniele Mingolla PUBLISH 8393@fosdem-2026@pentabarf.org

8393

CZSPSC-llama-cpp-vulkan

Vulkan API for Machine Learning? Competing with CUDA and ROCm in llama.cpp en

en_US

AI Plumbers 2026-01-31 14:45:00 +0100 2026-01-31 15:05:00 +0100 00:20:00:00 20260131T144500 20260131T150500 00:20:00:00

Vulkan API for Machine Learning? Competing with CUDA and ROCm in llama.cpp-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/CZSPSC-llama-cpp-vulkan/ UD2.120 (Chavanne) Ruben Ortlam PUBLISH 9691@fosdem-2026@pentabarf.org

9691

VYEMQR-running_tinygrad_and_ggml_on_microcontroller_npus

Running tinygrad and ggml on microcontroller NPUs en

en_US

AI Plumbers 2026-01-31 15:10:00 +0100 2026-01-31 15:15:00 +0100 00:05:00:00 20260131T151000 20260131T151500 00:05:00:00

Running tinygrad and ggml on microcontroller NPUs-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/VYEMQR-running_tinygrad_and_ggml_on_microcontroller_npus/ UD2.120 (Chavanne) Roman Shaposhnik PUBLISH 8280@fosdem-2026@pentabarf.org

8280

SPJDGF-energy-footprint-ai

The Hidden Cost of Intelligence: The Energy Footprint of AI from Code to GPU Kernels en

en_US

AI Plumbers 2026-01-31 15:20:00 +0100 2026-01-31 15:25:00 +0100 00:05:00:00 20260131T152000 20260131T152500 00:05:00:00

The Hidden Cost of Intelligence: The Energy Footprint of AI from Code to GPU Kernels-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/SPJDGF-energy-footprint-ai/ UD2.120 (Chavanne) Tushar Sharma PUBLISH 9692@fosdem-2026@pentabarf.org

9692

TDB3WN-ainativeprototyping

Lowering the barrier of entrance in AI-native system development en

en_US

AI Plumbers 2026-01-31 15:30:00 +0100 2026-01-31 15:35:00 +0100 00:05:00:00 20260131T153000 20260131T153500 00:05:00:00

Lowering the barrier of entrance in AI-native system development-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/TDB3WN-ainativeprototyping/ UD2.120 (Chavanne) Tanya Dadasheva PUBLISH 7659@fosdem-2026@pentabarf.org

7659

Z7LBYT-supercharging_llm_serving_with_dynamo

Supercharging LLM serving with Dynamo en

en_US

AI Plumbers 2026-01-31 15:40:00 +0100 2026-01-31 16:00:00 +0100 00:20:00:00 20260131T154000 20260131T160000 00:20:00:00

Supercharging LLM serving with Dynamo-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/Z7LBYT-supercharging_llm_serving_with_dynamo/ UD2.120 (Chavanne) Piotr Tarasiewicz PUBLISH 9394@fosdem-2026@pentabarf.org

9394

VGXWNS-taming_the_llm_zoo_with_docker_model_runner_inference_with_oci_artifacts_llama_c

Taming the LLM Zoo with Docker Model Runner: Inference with OCI Artifacts, llama.cpp, and vLLM en

en_US

AI Plumbers 2026-01-31 16:05:00 +0100 2026-01-31 16:25:00 +0100 00:20:00:00 20260131T160500 20260131T162500 00:20:00:00

Taming the LLM Zoo with Docker Model Runner: Inference with OCI Artifacts, llama.cpp, and vLLM-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/VGXWNS-taming_the_llm_zoo_with_docker_model_runner_inference_with_oci_artifacts_llama_c/ UD2.120 (Chavanne) Eric Curtin Dorin Geman PUBLISH 8120@fosdem-2026@pentabarf.org

8120

PD8WGF-from_infrastructure_to_production_a_year_of_self-hosted_llms

From Infrastructure to Production: A Year of Self-Hosted LLMs en

en_US

AI Plumbers 2026-01-31 16:30:00 +0100 2026-01-31 16:50:00 +0100 00:20:00:00 20260131T163000 20260131T165000 00:20:00:00

From Infrastructure to Production: A Year of Self-Hosted LLMs-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/PD8WGF-from_infrastructure_to_production_a_year_of_self-hosted_llms/ UD2.120 (Chavanne) Mateusz Charytoniuk Gosia Zagajewska Luiz Miguel PUBLISH 8764@fosdem-2026@pentabarf.org

8764

J9B9TR-et-platform-intro

A practical introduction to the ET platform. en

en_US

AI Plumbers 2026-01-31 16:55:00 +0100 2026-01-31 17:20:00 +0100 00:25:00:00 20260131T165500 20260131T172000 00:25:00:00

A practical introduction to the ET platform.-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/J9B9TR-et-platform-intro/ UD2.120 (Chavanne) Gianluca Guida PUBLISH 8165@fosdem-2026@pentabarf.org

8165

T3PSFN-zero_to_matmul_with_the_et-soc-1

Zero to matmul with the ET-SoC-1 en

en_US

AI Plumbers 2026-01-31 17:25:00 +0100 2026-01-31 17:45:00 +0100 00:20:00:00 20260131T172500 20260131T174500 00:20:00:00

Zero to matmul with the ET-SoC-1-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/T3PSFN-zero_to_matmul_with_the_et-soc-1/ UD2.120 (Chavanne) Peter Cawley PUBLISH 8432@fosdem-2026@pentabarf.org

8432

799WTL-all_in_risc-v_risc-v_all_in_ai_solving_real_ai_compute_challenges_with_deepcompu

All in RISC-V, RISC-V All in AI: Solving Real AI Compute Challenges with DeepComputing & Tenstorrent en

en_US

AI Plumbers 2026-01-31 17:50:00 +0100 2026-01-31 18:10:00 +0100 00:20:00:00 20260131T175000 20260131T181000 00:20:00:00

All in RISC-V, RISC-V All in AI: Solving Real AI Compute Challenges with DeepComputing & Tenstorrent-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/799WTL-all_in_risc-v_risc-v_all_in_ai_solving_real_ai_compute_challenges_with_deepcompu/ UD2.120 (Chavanne) Martin Chang Danfeng Zhang PUBLISH 8592@fosdem-2026@pentabarf.org

8592

QGKD3P-review_of_kernel_and_user-space_neural_processing_unit_npu_chips_support_on_linu

Review of kernel and user-space Neural Processing Unit (NPU) chips support on Linux en

en_US

AI Plumbers 2026-01-31 18:15:00 +0100 2026-01-31 18:35:00 +0100 00:20:00:00 20260131T181500 20260131T183500 00:20:00:00

Review of kernel and user-space Neural Processing Unit (NPU) chips support on Linux-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/QGKD3P-review_of_kernel_and_user-space_neural_processing_unit_npu_chips_support_on_linu/ UD2.120 (Chavanne) Jakov Petrina Trnski PUBLISH 8640@fosdem-2026@pentabarf.org

8640

AJLNVH-tt-boltz

TT-Boltz: Drug Discovery on Tenstorrent Hardware en

en_US

AI Plumbers 2026-01-31 18:40:00 +0100 2026-01-31 19:00:00 +0100 00:20:00:00 20260131T184000 20260131T190000 00:20:00:00

TT-Boltz: Drug Discovery on Tenstorrent Hardware-

PUBLIC CONFIRMED AI Plumbers https:/fosdem.org/2026/schedule/2026/schedule/event/AJLNVH-tt-boltz/ UD2.120 (Chavanne) Moritz Thüning