llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
-
Updated
Jul 11, 2025 - Python
#
gpu-performance
Here are 17 public repositories matching this topic...
Hands-on Machine Learning Infrastructure on Kubernetes. Using Microk8s/Ubuntu on Paperspace Cloud.
-
Updated
Mar 2, 2024 - Python
Evidence-driven PresentMon diagnostics and policy modeling paired with bounded owned-lab D3D11 runtime actuation.
windows open-source runtime d3d11 performance-analysis vram gpu-performance memory-optimization presentmon cpu-gpu frame-pacing readback frame-pipeline gpu-upload updatesubresource
-
Updated
Oct 16, 2026 - Python
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
kubernetes benchmarking performance gpu mcp cuda slurm inference codex gpu-performance llm vllm llm-inference gpu-profiling mcp-server agent-skills claude-code cuda-profiling
-
Updated
Oct 13, 2026 - Python
Comprehensive performance analysis of DeepSeek V3 quantization levels (FP16, Q8_0, Q4_0) on 16GB GPU environments.
quantization model-evaluation fp16 gpu-performance latency-analysis model-quantization inference-acceleration model-optimization llm-inference llm-optimization deepseek-v3 throughput-analysis
-
Updated
Sep 27, 2025 - Python
Interactive theoretical Kimi-K3 inference roofline calculator for H200, B300, and GB300
-
Updated
Aug 11, 2026 - Python
Reproducible long-context inference benchmark comparing vLLM, SGLang, and TensorRT-LLM on NVIDIA GB10.
benchmarking cuda nvidia gpu-performance long-context vllm llm-inference tensorrt-llm sglang prefix-caching
-
Updated
Sep 12, 2026 - Python
Python lab for exploring memory bandwidth, cache effects, and locality in accelerator workloads
performance-engineering hpc cuda memory-bandwidth gpu-performance roofline-model cache-locality tiling-optimization
-
Updated
Dec 24, 2025 - Python
Hybrid XGBoost + PyTorch ML system for semiconductor scaling analysis and real-time GPU FPS prediction with SHAP, LIME, and Scaling Integrated Gradients explainability.
pytorch xgboost bottleneck lime hardware-configuration gpu-performance shap explainability hardware-analytics semiconductor-scaling
-
Updated
Jun 10, 2026 - Python
Measured LLM inference studies on quantization, sparsity, GPU energy, KV-cache pruning, and vLLM serving.
-
Updated
Sep 7, 2026 - Python
Inference optimization experiments on Qwen2.5-3B with vLLM (throughput, latency, prefix cache exploration).
-
Updated
Apr 27, 2026 - Python
Reproducible H100 GPU-seconds/request study for 91 pinned Command A+ vLLM runs, with held-out evaluation, coverage diagnostics, and independent verification.
benchmarking reproducible-research cohere performance-modeling gpu-performance ml-systems vllm llm-inference nvidia-h100 serving-systems
-
Updated
Sep 1, 2026 - Python
Comprehensive machine learning benchmarking framework for AMD MI300X GPUs on Dell PowerEdge XE9680 hardware. Supports both inference (vLLM) and training workloads with containerized test suites, hardware monitoring, and analysis tools for performance, power efficiency, and scalability research across the complete ML pipeline.
machine-learning deep-learning pytorch performance-analysis gpu-computing rocm hardware-monitoring gpu-monitoring distributed-training gpu-performance amd-gpu gpu-parallelism vllm power-efficiency llm-benchmarking containerized-testing ai-infrastructure dell-poweredge amd-mi300x scalability-testing
-
Updated
Aug 15, 2025 - Python
Reproducible CUDA kernel optimization and vLLM inference profiling on NVIDIA GPUs.
performance-engineering cuda pytorch gpu-performance vllm llm-inference nsight-systems nsight-compute
-
Updated
Sep 7, 2026 - Python
Trace a PyTorch fusion, verify Triton candidates against eager, and compare real T4 timings. failures recorded.
-
Updated
Oct 1, 2026 - Python
Correctness-first verification, profiling, and RL rewards for AI-written Triton kernels.
-
Updated
Jul 26, 2026 - Python
Adjust GPU core clock and memory speeds to improve frame rates and hardware performance in gaming applications.
gpu-performance gpu-tool gpu-booster gpu-overclock gpu-tweak gpu-overclock-tool gpu-overclocker gpu-overclock-2026 gpu-overclock-free gpu-overclock-download gpu-overclock-github gpu-overclock-pc best-gpu-overclock gpu-overclock-exe gpu-overclock-safe gpu-overclock-tool-software msi-afterburner-alternative gpu-undervolt gpu-clock-tool nvidia-overclock
-
Updated
Oct 14, 2026 - Python
Add this topic to your repo
To associate your repository with the gpu-performance topic, visit your repo's landing page and select "manage topics."