thedatamates
Popular repositories Loading
-
-
ducklake
ducklake PublicForked from duckdb/ducklake
DuckLake is an integrated data lake and catalog format
C++ 1
-
-
candle-lora
candle-lora PublicForked from EricLBuehler/candle-lora
Low rank adaptation (LoRA) for Candle.
Rust
-
-
candle-vllm
candle-vllm PublicForked from EricLBuehler/candle-vllm
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
Rust
Repositories
- tokenspeed Public Forked from lightseekorg/tokenspeed
TokenSpeed is a speed-of-light LLM inference engine.
thedatamates/tokenspeed’s past year of commit activity - NVIDIA-TransformerEngine Public Forked from NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
thedatamates/NVIDIA-TransformerEngine’s past year of commit activity - renderers Public Forked from PrimeIntellect-ai/renderers
Programmable chat templates for LLM training and inference.
thedatamates/renderers’s past year of commit activity - flash-attention Public Forked from Dao-AILab/flash-attention
Fast and memory-efficient exact attention
thedatamates/flash-attention’s past year of commit activity - NVIDIA-NeMo-Automodel Public Forked from NVIDIA-NeMo/Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
thedatamates/NVIDIA-NeMo-Automodel’s past year of commit activity - NVIDIA-Megatron-LM Public Forked from NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
thedatamates/NVIDIA-Megatron-LM’s past year of commit activity - NVIDIA-NeMo-Megatron-Bridge Public Forked from NVIDIA-NeMo/Megatron-Bridge
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
thedatamates/NVIDIA-NeMo-Megatron-Bridge’s past year of commit activity - vllm Public Forked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
thedatamates/vllm’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…