dsingal0

flux_fp8

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

landing_page

Landing page for qdrant.tech

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

test_70b

truss-examples

Examples of models deployable with Truss

unmanic-documentation

All documentation for Unmanic

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

dsingal0/flux_fp8

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

dsingal0/landing_page

Landing page for qdrant.tech

dsingal0/TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

dsingal0/test_70b

dsingal0/truss-examples

Examples of models deployable with Truss

dsingal0/unmanic-documentation

All documentation for Unmanic

dsingal0/unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

dsingal0/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs