|
From text to task: Constrained generation for structured extraction in R1
|
-- |
2025-02-01 |
Active |
5,968 |
--
|
|
DeepSeek R1 Just Got Eyes with Fireworks AI Document Inlining
|
-- |
2025-02-05 |
Active |
2,194 |
--
|
|
DeepSeek v3 and R1 Model Architecture: Why it's powerful and economical
|
-- |
2025-02-07 |
Active |
1,663 |
--
|
|
Enabling Function Calling in DeepSeek v3: Bridging the Gap Between Text and Action
|
-- |
2025-02-14 |
Active |
2,159 |
--
|
|
Fine-Tuning DeepSeek v3 & R1 to optimize quality, latency, & cost
|
-- |
2025-03-12 |
Active |
890 |
--
|
|
Fireworks AI Now Supports NVIDIA NIM Deployments for Blazing AI Inference
|
-- |
2025-03-18 |
Active |
851 |
--
|
|
Faster, more efficient DeepSeek on the Fireworks AI Developer Cloud
|
-- |
2025-03-18 |
Active |
386 |
--
|
|
Building Enterprise-Scale RAG Systems with Fireworks AI and MongoDB Atlas
|
-- |
2025-04-09 |
Active |
1,702 |
--
|
|
Optimizing Llama 4 Maverick on Fireworks AI
|
-- |
2025-04-28 |
Active |
1,151 |
--
|
|
Qwen 3 on Fireworks AI: Controllable Chain-of-Thought and Tool Calling at Frontier Scale
|
-- |
2025-05-06 |
Active |
815 |
--
|
|
Supervised Fine-Tuning (SFT) with LoRA on Fireworks AI: Tutorial
|
-- |
2025-05-12 |
Active |
1,037 |
--
|
|
Agentic AI Systems
|
-- |
2025-05-19 |
Active |
1,900 |
--
|
|
Building an open-source Browser Agent on Fireworks AI
|
-- |
2025-05-21 |
Active |
2,613 |
--
|
|
FireAttention V4: Industry-Leading Latency and Cost Efficiency with FP4
|
-- |
2025-05-28 |
Active |
1,011 |
--
|
|
Fireworks DevDay 2025 Wrapped
|
-- |
2025-05-29 |
Active |
963 |
--
|
|
Building a High‑Quality Synthetic Data Pipeline for Supervised Fine‑Tuning
|
-- |
2025-06-04 |
Active |
972 |
--
|
|
Reinforcement Fine Tuning (Beta): Train expert open models to surpass closed frontier models
|
-- |
2025-06-09 |
Active |
885 |
--
|
|
Building AI agents with the Fireworks Experimentation Platform (GA) and Build SDK (Beta)
|
-- |
2025-06-11 |
Active |
1,241 |
--
|
|
Vision Model Platform Updates: Enhanced Capabilities and New Features
|
-- |
2025-06-12 |
Active |
1,133 |
--
|
|
Introducing Supervised Fine Tuning V2
|
-- |
2025-06-13 |
Active |
735 |
--
|
|
3D FireOptimizer: Automating the Multi-Dimensional Tradeoffs in LLM Serving
|
-- |
2025-06-14 |
Active |
1,385 |
--
|
|
Build for Scale with Fireworks Virtual Cloud (GA)
|
-- |
2025-06-16 |
Active |
1,088 |
--
|
|
Unlock Your Tools: Fireworks Adds OpenAI-Response API with MCP Support (Beta)
|
-- |
2025-06-22 |
Active |
1,088 |
--
|
|
Introducing FLUX.1 Kontext on Fireworks
|
-- |
2025-07-09 |
Active |
372 |
--
|
|
Using Model-as-a-Judge for Reward in Reinforcement Fine Tuning
|
-- |
2025-07-10 |
Active |
765 |
--
|
|
Understanding Function Calling: The Bridge to Agentic AI
|
-- |
2025-07-11 |
Active |
1,203 |
--
|
|
Fireworks AI Now Supports Amazon SageMaker
|
-- |
2025-07-15 |
Active |
448 |
--
|
|
Deep-dive into MuonClip: Fixing Attention Score Explosions in Transformer Training
|
-- |
2025-07-15 |
Active |
2,699 |
--
|
|
Sentient & Fireworks Powers Decentralized AI At Viral Scale
|
-- |
2025-07-17 |
Active |
1,333 |
--
|
|
A Deep Dive into MLA training/inference difference and why QK-Clip from Kimi is such an elegant idea
|
-- |
2025-07-22 |
Active |
5,418 |
--
|
|
VibeRL: When AI Trains AI
|
-- |
2025-07-22 |
Active |
697 |
--
|
|
How Notion Cuts Latency 4x and Scales Enterprise AI Workflows with Fireworks AI
|
-- |
2025-07-25 |
Active |
514 |
--
|
|
Introducing Vision-Language Model Fine-tuning: Tailor VLMs to Your Domain
|
-- |
2025-07-29 |
Active |
885 |
--
|
|
Fireworks Real-World Benchmarks: Find the Best OSS Model for the Job
|
-- |
2025-07-30 |
Active |
681 |
--
|
|
Run bulk async workloads with Fireworks Batch API
|
-- |
2025-07-31 |
Active |
419 |
--
|
|
Qwen3 Decoded: Choosing the Right Model For Your Task
|
-- |
2025-08-01 |
Active |
2,790 |
--
|
|
Kimi K2: Deep Dive into model performance and use-cases
|
-- |
2025-08-01 |
Active |
989 |
--
|
|
Announcing Eval Protocol
|
-- |
2025-08-04 |
Active |
783 |
--
|
|
Introducing OpenAI gpt-oss (20b & 120b)
|
-- |
2025-08-05 |
Active |
804 |
--
|
|
Quality first: how Fireworks.ai is the go-to place for gpt-oss
|
-- |
2025-08-12 |
Active |
1,030 |
--
|
|
Test-Driven Agent Development with Eval Protocol
|
-- |
2025-08-14 |
Active |
1,501 |
--
|
|
Your AI Benchmark is Lying to You. Here's How We Caught It
|
-- |
2025-08-15 |
Active |
4,108 |
--
|
|
LLM Eval Driven Development with Claude Code
|
-- |
2025-08-25 |
Active |
1,394 |
4
|
|
DeepSeek V3.1 now on Fireworks AI!
|
-- |
2025-08-26 |
Active |
613 |
--
|
|
Understanding Embeddings and Reranking at Scale
|
-- |
2025-09-12 |
Active |
1,546 |
--
|
|
Traces Are All You Need (to rank LLMs)
|
-- |
2025-09-22 |
Active |
2,091 |
--
|
|
Launching Fireworks for Startups Program!
|
-- |
2025-10-01 |
Active |
473 |
--
|
|
Production-Ready AI Agents with Optimized Inference with AWS AgentCore
|
-- |
2025-10-02 |
Active |
401 |
--
|
|
Global Fast Food Group Transforms Drive-Thru with Real-Time Voice Intelligence with Fireworks
|
-- |
2025-10-06 |
Removed |
1,019 |
--
|
|
Fireworks Streaming Transcription: 300ms with Whisper-v3-large-quality
|
-- |
2025-10-06 |
Removed |
1,119 |
--
|
