mhendrey
Follow
-
vllm Public
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Python Apache License 2.0 UpdatedJan 24, 2025 -
Mad-Llama-Disease Public
Investigating Llama-3.1's penchant for failing to generate the end-of-string token and thus generating gibberish until the context window has been filled.
Python GNU General Public License v3.0 UpdatedJan 15, 2025 -
triton-florence2 Public
Forked from TritonsProngs/triton-florence2A Triton Inference Server model repository hosting the Florence2 model.
Python GNU General Public License v3.0 UpdatedJan 4, 2025 -
TritonsProngs Public
Collection of Triton Inference Server deployment packages.
-
triton-translation-tutorial Public
Provides a step-by-step tutorial on building a machine translation server using NVIDIA's Triton Inference Server. The tutorial starts with a basic deployment of the translation service, and then it…
-
vekterdb Public
Transform any SQLAlchemy compliant database into a vector database by adding any type of a FAISS index in order to perform approximate nearest neighbor (ANN) search on the vector column.
Python GNU General Public License v3.0 UpdatedFeb 2, 2024 -
lakeshack Public
A simplified data lake, more of a data shack, optimized for retrieving filtered records from Parquet files.
-
pocket_dimension Public
A memory-efficient, dense, random projection of sparse vectors
-
sketchnu Public
Numba implementations of some sketch algorithms.
Python GNU General Public License v3.0 UpdatedMar 3, 2023 -
sketchnu-feedstock Public
Forked from conda-forge/sketchnu-feedstockA conda-smithy repository for sketchnu.
BSD 3-Clause "New" or "Revised" License UpdatedFeb 25, 2023 -
staged-recipes Public
Forked from conda-forge/staged-recipesA place to submit conda recipes before they become fully fledged conda-forge feedstocks
Python BSD 3-Clause "New" or "Revised" License UpdatedApr 28, 2022