Jul 03

DSpark: Deepseek improves GPU utilization with token rates - | Golem.de:

Speculative decoding allows for significantly better GPU utilization ...

golem.de/news/dspark-deepseek-verbessert-mit-token-raten-die-gpu-auslastung-2607-210485.html

DSpark: Deepseek improves GPU utilization with token rates - | Golem.de

Story Details

Last Updated
Total Articles	3

Main Topics

Research

#research-69a6abc5c6a59

systematic study undertaken to increase knowledge

Large language model

#large-language-model

language model built with very large amounts of texts

Application software

#application-software

software program or group of programs designed for end-users

Similar to This

marktechpost.com 6h

DeepSeek Open-Sources DeepInfer, the Inference Framework Behind DeepSeek-V4.1-Flash

marktechpost.com/2026/10/20/deepseek-deepinfer-open-source-inference-framework/

0 similar articles

github.com Oct 20

GitHub - deepseek-ai/DeepInfer: DeepInfer: High-performance, large-scale inference framework for DeepSeek models

github.com/deepseek-ai/DeepInfer

26 similar articles

142

VentureBeat

Credibility C

Oct 19

MiniMax's new M3.1 Flash beats DeepSeek and Opus 5 on a key business benchmark at lower cost — but with a high hallucination rate

venturebeat.com/technology/minimaxs-new-m3-1-flash-beats-deepseek-and-opus-5-on-a-key-business-benchmark-at-lower-cost-but-with-a-high-hallucination-rate

5 similar articles

github.com Sep 09

GitHub - ciprianveg/3090-vllm: Contribute to ciprianveg/3090-vllm development by creating an account on GitHub.

github.com/ciprianveg/3090-vllm

0 similar articles

github.com Aug 27

[feat] support dspark (Nanbeige4.2-3B) by zqlcode · Pull Request #27730 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/27730

0 similar articles

github.com Aug 23

GitHub - Agusx1211/llama-cpp-ds4f-m2-ultra: LLM inference in C/C++: LLM inference in C/C++. Contribute to Agusx1211/llama-cpp-ds4f-m2-ultra development by ...

github.com/Agusx1211/llama-cpp-ds4f-m2-ultra

0 similar articles

github.com Aug 20

spec : support DSpark for LFM2 models by tdakhran · Pull Request #27383 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/27383

0 similar articles

github.com Aug 10

GitHub - tonyd2wild/DeepSeek-v4-Flash-0731-DSpark-1M-NVFP4-KV-2x-DGX-Spark: DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

github.com/tonyd2wild/DeepSeek-v4-Flash-0731-DSpark-1M-NVFP4-KV-2x-DGX-Spark

0 similar articles

286

github.com Aug 11

GitHub - raullenchai/twinspark: Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster ...

github.com/raullenchai/twinspark

0 similar articles

github.com Aug 02

DeepseekV4 MTP + DSpark by am17an · Pull Request #25784 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an ...

github.com/ggml-org/llama.cpp/pull/25784

0 similar articles

126

github.com Aug 01

GitHub - haraldh/llama.cpp at dspark-dsv4: LLM inference in C/C++. Contribute to haraldh/llama.cpp development by creating an account on GitHub.

github.com/haraldh/llama.cpp/tree/dspark-dsv4

0 similar articles

github.com Jul 28

spec: add DSpark speculative decoding by wjinxu · Pull Request #25173 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/25173

0 similar articles

VentureBeat

Jul 12

DeepSeek cut prices 75%. The 100x problem remains

venturebeat.com/orchestration/deepseek-cut-prices-75-the-100x-problem-remains

0 similar articles

2 1

github.com Jun 29

DeepSeek V4 by am17an · Pull Request #24162 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on ...

github.com/ggml-org/llama.cpp/pull/24162

0 similar articles

Nvidia

Jun 30

How NVIDIA’s Inference Software Stack Powers the Lowest Token Cost: Baseten, Cognition, Deep Infra, Together AI and Cursor are seeing compounding value from ...

blogs.nvidia.com/blog/inference-software-lowest-token-cost/

The New Stack May 13

The disappearing AI middle class: OpenAI and DeepSeek pricing bets have split the market. Here's why the AI middle class is disappearing and how developers ...

thenewstack.io/disappearing-ai-middle-class/

0 4

The New Stack Apr 26

The disappearing AI middle class: OpenAI and DeepSeek pricing bets have split the market. Here's why the AI middle class is disappearing and how developers ...

thenewstack.io/disappearing-ai-middle-class/

0 similar articles

4 0

Wccftech Apr 02

NVIDIA Is Among the First to Submit MLPerf Inference v6.0 Benchmarks With Blackwell Ultra, and It’s Total Domination Over Competitors

wccftech.com/nvidia-is-among-the-first-to-submit-mlperf-inference-v6-0-benchmarks/

2 similar articles