LLM performance

11 posts · 7 sources

Together AIBlog28 Aug

GLM-5.3 vs. GLM-5.3 Flash on DeepSWE: Cost, Coding, and Routing

PineconeBlog6 Aug

Nexus GA: It's the Knowledge, Not the Models

HexBlog9 Jun

We had to build new evals for Fable

AnthropicBlog5 Jun

Making Claude a chemist

Together AIBlog26 Mar

Plan, divide, and conquer: How weak models excel at long context tasks

CerebrasBlog8 Jan

Cerebras

Together AIBlog3 Dec

Introducing AutoJudge: Streamlined inference acceleration via automated dataset curation

CerebrasBlog19 Mar

Cerebras brings instant inference to Mistral Le Chat

CerebrasBlog17 Mar

Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference

BasetenBlog6 Feb

Unlocking the full power of NVIDIA H100 GPUs for ML inference with TensorRT

QdrantBlog28 Feb

Pienso & Qdrant: Future Proofing Generative AI for Enterprise-Level Customers