A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Go ahead and axolotl questions
Ongoing research training transformer models at scale
🏗️ Fine-tune, build, and deploy open-source LLMs easily!
Minimalistic large language model 3D-parallelism training
PyTorch native quantization and sparsity for training and inference
1 capture since 2026-05-25
AI agent config detected
Key config paths
.agents
.claude
.coderabbit.yaml
AGENTS.md
CLAUDE.md
tools/debugger/CLAUDE.md
1 more config path detected.
.agents
.agents/TOOLING.md
.claude
.claude/clusters.yaml.example
.claude/scripts
.claude/scripts/sync-upstream-skills.sh
.claude/skills
.claude/skills/accessing-mlflow
.claude/skills/accessing-mlflow/SKILL.md
.claude/skills/common
.claude/skills/common/credentials.md
.claude/skills/common/environment-setup.md
.claude/skills/common/remote-execution.md
.claude/skills/common/remote_exec.sh
.claude/skills/common/slurm-setup.md
.claude/skills/common/workspace-management.md
.claude/skills/compare-results
.claude/skills/compare-results/SKILL.md
.claude/skills/compare-results/tests
.claude/skills/compare-results/tests/evals.json
.claude/skills/debug
.claude/skills/debug/SKILL.md
.claude/skills/deployment
.claude/skills/deployment/references
Showing the first 24 paths. 64 more detected.