Gregory-Pereira/flashinfer
FlashInfer: Kernel Library for LLM Serving
Sr. Machine Learning Engineer @ Red Hat | Inference Engineering | Building llm-d: distributed inference for LLMs on Kubernetes
Repositories
Gregory-Pereira/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Gregory-Pereira/llm-d
llm-d is a Kubernetes-native high-performance distributed LLM inference framework
Gregory-Pereira/envoy-ai-gateway
Manages Unified Access to Generative AI Services built on Envoy Gateway
Gregory-Pereira/speculators
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Gregory-Pereira/llm-d-router
Inference scheduler for llm-d
Gregory-Pereira/beads
Beads - A memory upgrade for your coding agent
Gregory-Pereira/llm-d-latency-predictor
Latency prediction service for ML-model based scoring with llm-d-inference-scheduler
Gregory-Pereira/rfe-creator
Gregory-Pereira/strat-creator
Gregory-Pereira/disconnected-readiness-scorer
Disconnected readiness scanner for RHOAI component repos — scores repos for air-gapped/disconnected deployment compatibility
Gregory-Pereira/terraform-gitlab-runners-module
Gregory-Pereira/snyk-jira-reporter
A github workflow to automate the creation of bugs in jira by reading the snyk scan reports.
Gregory-Pereira/batch-gateway
The batch gateway is an llm-d implementation of the OpenAI batch inference API
Gregory-Pereira/vllm-plugin-FL
A vLLM plugin built on the FlagOS unified multi-chip backend.
Gregory-Pereira/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Gregory-Pereira/flash-attention
Fast and memory-efficient exact attention
Gregory-Pereira/vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
Gregory-Pereira/Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Gregory-Pereira/llm-d-infra
repo for CI and infrastructure required to maintain llm-d org member repos
Gregory-Pereira/llm-d-infra-charts
Gregory-Pereira/llama-stack-on-ocp
Collection of demos for building Llama Stack based apps on OpenShift
Gregory-Pereira/konflux-central
Central repository for managing Konflux resource files. This streamlines maintenance by consolidating configurations and leveraging GitHub Actions for automated syncing.
Gregory-Pereira/DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Gregory-Pereira/vllm-skills
Agent skills for vLLM
Gregory-Pereira/odh-konflux-central
To centrally store all the Konflux artifacts
Gregory-Pereira/RHOAI-Build-Config
Gregory-Pereira/gitdm
📜Fork for tracking CNCF projects
Gregory-Pereira/nvshmem
NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.
Gregory-Pereira/workload-variant-autoscaler
Variant optimization autoscaler for distributed inference workloads