deepseek-ai/DeepSeek-V4-Pro-0813
New text-generation model. Tags: deepseek_v4, text-generation, conversational, arxiv:2606.19348, license:mit, 8-bit, fp8
nl♥ 625
DeepSeek
138
15
Tiered KV cache for large LLMs on Amazon SageMaker HyperPod with Curvine
Running large language model inference at scale forces a KV cache trade-off: oversized GPU instances or slow time-to-first-token. This post builds a tiered KV cache on Amazon SageMaker HyperPod that extends the cache into a shared, distributed NVMe pool with Curvine, so replicas reuse cache at near-local-disk speeds on cost-efficient instances.
en
NVIDIA and Local AI Community Fuel Open Source Models and Intelligent Agents
The open source ecosystem is making it easier for AI enthusiasts and developers to build, customize and run increasingly capable agents locally. Throughout August, NVIDIA is celebrating the partners and open source communities moving local AI forward, along with the models, applications and tools emerging across the ecosystem. That includes NVIDIA’s latest open models, software […]
en
DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Coding
We ran 900 DeepSWE rollouts on DeepSeek-V4 Flash and GPT-5.6 Luna. Luna leads pass@1 by 14 points; DeepSeek delivers 4.8x the solves per dollar.
en
deepseek-ai/DeepSeek-V4-Flash-0731
New text-generation model. Tags: deepseek_v4, text-generation, conversational, arxiv:2606.19348, license:mit, eval-results, 8-bit, fp8
nl♥ 3546
Serving DeepSeek-V4: why million-token context is an inference systems problem
DeepSeek-V4 makes million-token context a serving-systems problem. Together AI explores the inference work behind V4 on NVIDIA HGX B200, including compressed KV layouts, prefix caching, kernel maturity, and endpoint profiles for long-context workloads.
en
Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling
Overview of adaptive parallel reasoning. What if a reasoning model could decide for itself when to decompose and parallelize independent subtasks, how many concurrent threads to spawn, and how to coordinate them based on the problem at hand? We provide a detailed analysis of recent progress in the field of parallel reasoning, especially Adaptive Parallel Reasoning. Disclosure: this post is…
en
DeepSeek-V4 Pro now available on Together AI
DeepSeek-V4 Pro is now available on Together AI with 512K context, controllable reasoning modes, and cached-input pricing for long-context reasoning workloads like code agents, document intelligence, and research synthesis.
en
What do LLMs think when you don't tell them what to think about?
What do language models generate when you don't tell them what to generate? New research reveals that LLM families have distinct 'knowledge priors'—GPT models default to code and math, Llama favors narratives, DeepSeek generates religious content, and Qwen outputs exam questions.
en
Claude Code costs up to $200 a month. Goose does the same thing for free.
The artificial intelligence coding revolution comes with a catch: it's expensive. Claude Code , Anthropic's terminal-based AI agent that can write, debug, and deploy code…
en
Together AI delivers fastest inference for the top open-source models
Together AI achieves up to 2x faster inference for top open-source models like Qwen, DeepSeek, and Kimi through GPU optimization, advanced speculative decoding, and FP4 quantization—ranking #1 in speed benchmarks on NVIDIA Blackwell architecture.
en