DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks

DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s). Launchers, run records, measured numbers. Older vLLM lanes kept.

tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks

View on GitHub ↗

DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s). Launchers, run records, measured numbers. Older vLLM lanes kept.

DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks grew +19.1% in the last 30 days, ranks 262nd of 397 in Production Serving & Deployment, last commit 26 days ago.

Star trajectory

50 days tracked
2026-10-03168 stars today2026-11-22
Momentum

+19.1% in 30d, above the Production Serving & Deployment median of +1.3%.

Maintenance

Last commit 26 days ago, staler than the median of 3d.

How it compares in Production Serving & Deployment

DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks
168
stars
+19.1% 30d
commit 26 days ago
Production Serving & Deployment median
272
stars
+1.3% 30d
commit ~3d ago
Leader · vllm
97.3k
stars
+2.2% 30d
commit today

Ranked 262nd of 397 by stars.

Ranked by shared tags, then keywords, then stars
  1. Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    +25 (+3.5%) in 30d · Committed yesterday · Rust · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization, Distributed Inference

  2. JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs…

    +3 (+0.6%) in 30d · Committed 320d ago · Python · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization, Distributed Inference

  3. A high-performance inference system for large language models, designed for production environments.

    -1 (-0.2%) in 30d · Committed 338d ago · C++ · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization, Distributed Inference

  4. Kindi 0.6.1: fast local LLM inference on low-cost GPUs and CPUs. DeepSeek-V4.1-Flash (552B) at 18.7 tok/s on…

    Committed 5d ago · Python · AGPL-3.0

    Shares Production Serving & Deployment, Distributed Inference, Inference Optimization

  5. Tensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster…

    +1 (+0.6%) in 30d · Committed 2d ago · Go · Apache-2.0

    Shares Distributed Inference, Production Serving & Deployment, Inference Optimization

  6. Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely…

    -22 (-41%) in 30d · Committed today · Go · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference, Inference Optimization

  7. High Performance Serving Runtime For Interactive Super Intelligence System

    +299 (+19%) in 30d · Committed today · Python · Apache-2.0

    Shares Production Serving & Deployment, Distributed Inference, Inference Optimization

  8. 🧱 Experimental library for building inference engines

    Committed today · Python · Apache-2.0

    Shares Inference Optimization, Production Serving & Deployment, Distributed Inference

  9. Accelerate inference without tears

    -1 (-0.3%) in 30d · Committed 303d ago · Python · MIT

    Shares Inference Optimization, Production Serving & Deployment, Distributed Inference

  10. Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service…

    -1 (-0.6%) in 30d · Committed 349d ago · Python · Apache-2.0

    Shares Production Serving & Deployment, Inference Optimization, Distributed Inference

Language
Python
License
MIT License
Contributors
4
Forks
24
Watchers
3
Open issues
1
Releases
0
Created
2026-09-10
Stars this week
+4

You've seen where DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks stands today.

Get the moves before everyone else: the 5 Production Serving & Deployment repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks?

Claim this page to add your own call-to-action.

Claim this page