Comparison
FasterTransformer vs exllama
Verdict
Pick FasterTransformer if highly optimized transformer encoder and decoder for inferencing, supporting BERT and GPT on various frameworks like TensorFlow, PyTorch; pick exllama if exLlama provides a memory-efficient implementation of the LLaMa model with support for quantized weights, primarily aimed at users with NVIDIA GPUs from the 30-series onwards.
Markdown twin · FasterTransformer alternatives · exllama alternatives
GraphCanon updated 2w
vs
Trust & integrity
| Signal | FasterTransformer | exllama |
|---|---|---|
| Maintenance | Dormant (862d since push) As of 2w · github_public_v1 | Dormant (1041d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 2w · github_public_v1 | Not a fork · Personal account As of 2w · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1mo · osv@v1 | Published findings As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- FasterTransformer
- Transformer related optimization including BERT and GPT
- exllama
- Memory-efficient rewrite of HF transformers for Llama with quantized weights
Stars
- FasterTransformer
- 6.4k
- exllama
- 2.9k
Forks
- FasterTransformer
- 935
- exllama
- 220
Open issues
- FasterTransformer
- 289
- exllama
- 65
Language
- FasterTransformer
- C++
- exllama
- Python
Adopt for
- FasterTransformer
- Highly optimized transformer encoder and decoder for inferencing, supporting BERT and GPT on various frameworks like TensorFlow, PyTorch.
- exllama
- ExLlama provides a memory-efficient implementation of the LLaMa model with support for quantized weights, primarily aimed at users with NVIDIA GPUs from the 30-series onwards.
Persona
- FasterTransformer
- -
- exllama
- -
Runtime
- FasterTransformer
- -
- exllama
- -
License
- FasterTransformer
- Apache-2.0
- exllama
- MIT
Last pushed
- FasterTransformer
- Mar 27, 2024
- exllama
- Sep 30, 2023
Categories
- FasterTransformer
- Inference & Serving
- exllama
- Inference & Serving, LLM Frameworks
Trust and health
Days since push
- FasterTransformer
- 862d
- exllama
- 1041d
Open issues (now)
- FasterTransformer
- 289
- exllama
- 65
Owner type
- FasterTransformer
- Organization
- exllama
- User
OSV dependency advisories
- FasterTransformer
- No lockfile (source not queried)
- exllama
- Published findings
Full report
- FasterTransformer
- Trust report
- exllama
- Trust report
Choose FasterTransformer if…
- FasterTransformer is primarily C++; exllama is Python.
- License: FasterTransformer is Apache-2.0, exllama is MIT.
- Tags unique to FasterTransformer: bert, cublas, cublaslt, cuda.
- When aiming for high performance with GPU-based FP16 computations for BERT or GPT models specifically.
When NOT to use FasterTransformer
- If looking for active development and latest improvements on LLM Inference as NVIDIA recommends TensorRT-LLM over FasterTransformer now.
- When specific frameworks not including TensorFlow, PyTorch, or Triton are required.
Choose exllama if…
- exllama is primarily Python; FasterTransformer is C++.
- License: exllama is MIT, FasterTransformer is Apache-2.0.
- Tags unique to exllama: docker, llama model, memory-efficient, nvidia gpu.
- Also covers LLM Frameworks.
- exllama ships Docker support for self-hosted deployment.
- - When deploying LLaMa models on NVIDIA GPUs from the 30-series or later that have strong FP16 support.
When NOT to use exllama
- - If you are operating older GPUs such as Pascal series, which lack robust FP16 support; alternatives like AutoGPTQ might perform better.
- - In scenarios that involve AMD GPU hardware (due to limited testing and optimization efforts).
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (NVIDIA/FasterTransformer) · observed Aug 7, 2026
- GitHub forks (NVIDIA/FasterTransformer) · observed Aug 7, 2026
- Last push (NVIDIA/FasterTransformer) · observed Mar 27, 2024
- License file (Apache-2.0) · observed Aug 7, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (turboderp/exllama) · observed Aug 7, 2026
- GitHub forks (turboderp/exllama) · observed Aug 7, 2026
- Last push (turboderp/exllama) · observed Sep 30, 2023
- License file (MIT) · observed Aug 7, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: FasterTransformer 6.4k · exllama 2.9k (synced Aug 7, 2026).
Common questions
- What is the difference between FasterTransformer and exllama?
- FasterTransformer: Transformer related optimization including BERT and GPT. exllama: Memory-efficient rewrite of HF transformers for Llama with quantized weights. See the comparison table for live GitHub stats and shared categories.
- When should I choose FasterTransformer over exllama?
- Choose FasterTransformer over exllama when FasterTransformer is primarily C++; exllama is Python; License: FasterTransformer is Apache-2.0, exllama is MIT; Tags unique to FasterTransformer: bert, cublas, cublaslt, cuda; When aiming for high performance with GPU-based FP16 computations for BERT or GPT models specifically.
- When should I choose exllama over FasterTransformer?
- Choose exllama over FasterTransformer when exllama is primarily Python; FasterTransformer is C++; License: exllama is MIT, FasterTransformer is Apache-2.0; Tags unique to exllama: docker, llama model, memory-efficient, nvidia gpu; Also covers LLM Frameworks; exllama ships Docker support for self-hosted deployment; - When deploying LLaMa models on NVIDIA GPUs from the 30-series or later that have strong FP16 support.
- When should I avoid FasterTransformer?
- If looking for active development and latest improvements on LLM Inference as NVIDIA recommends TensorRT-LLM over FasterTransformer now. When specific frameworks not including TensorFlow, PyTorch, or Triton are required.
- When should I avoid exllama?
- - If you are operating older GPUs such as Pascal series, which lack robust FP16 support; alternatives like AutoGPTQ might perform better. - In scenarios that involve AMD GPU hardware (due to limited testing and optimization efforts).
- Is FasterTransformer or exllama more popular on GitHub?
- FasterTransformer has more GitHub stars (6,446 vs 2,937). Stars measure visibility, not whether either tool fits your constraints.
- Are FasterTransformer and exllama open source?
- Yes - both are open-source projects on GitHub (FasterTransformer: Apache-2.0, exllama: MIT).
- Where can I find alternatives to FasterTransformer or exllama?
- GraphCanon lists graph-backed alternatives at FasterTransformer alternatives and exllama alternatives (FasterTransformer markdown twin, exllama markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, FasterTransformer or exllama?
- FasterTransformer: Dormant. exllama: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for FasterTransformer and exllama?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: FasterTransformer trust report; exllama trust report.