Home / Companies / Fireworks AI / Hacker News

Fireworks AI on HN

30 posts with 1+ points since 2022

Filters
Since:
Posts by Month (30 total)
Hacker News Posts
Title Points Comments Date
Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA 877 450 2026-07-21
Fireworks: Function Calling Model and API 53 18 2023-12-21
Fireworks F1: A Breakthrough in Complex Reasoning with Compound AI 17 8 2024-11-18
FireFunction V1 – GPT-4-level function calling model – 4x faster, open weights 7 0 2024-02-22
Fireworks – Announcing our Series D and $1B ARR 5 0 2026-07-16
How are people training this LLMs? Dont they need lot of money? 4 1 2024-01-19
LLM Eval Driven Development with Claude Code 4 0 2025-08-28
How we fixed prompt injection for all models on Fireworks 4 1 2026-04-23
Optimizing MiniMax M3 Sparse Attention on Nvidia Blackwell 4 0 2026-07-13
DeepSeek V4 Pro: Validating Frontier Models for Production 3 0 2026-04-28
Multi-Query Attention Is All You Need 3 0 2023-07-13
Matching frontier performance through training and harness engineering 3 0 2026-06-08
FireAttention – Serving Mixtral and open-source MoE models at 4x speed vs. … 3 0 2024-01-09
Accelerating Code Completion with Fireworks Fast LLM Inference 2 0 2023-10-11
Turn Your LLM into a Calibrated Classifier for $2 2 0 2026-02-20
Why Building Mega Clusters Is Wrong 2 0 2026-03-21
The Benchmark Gap: What It Takes to Ship Kimi K2.5 2 0 2026-02-16
Frontier RL Is Cheaper Than You Think 2 0 2026-03-26
Agents Don't Fail on Intelligence, They Fail on Execution 2 0 2026-05-21
Deep-Dive into LLM Fine-Tuning 2 0 2026-02-23
FireAttention V3: Enabling AMD as a Viable Alternative for GPU Inference 1 0 2024-10-16
Fireworks.ai: Language Model Serving with Custom LoRA Fine-Tuned Models 1 0 2023-08-18
Can DeepSeek R1 Teach Better Than Humans? 1 0 2025-02-05
Document Inlining: Crossing the Modality Gap with Compound AI 1 0 2024-12-23
Natural Language → SQL with Reinforcement Fine Tuning (RFT) 1 0 2025-08-18
Turning Production Logs into Evaluation Datasets: A Data-Driven Approach 1 0 2026-02-16
DPO, your simplest RL pipeline with two rollouts 1 0 2026-02-18
How to accurately and interpretably evaluate the quant effect of large models? 1 0 2024-08-09
GPUs on-demand: Not serverless, not reserved, but some third thing 1 0 2024-06-07
Serving Open Source Models 4x faster than vLLM by quantizing with ~no … 1 0 2024-03-21
Plushcap, by Matt Makai. 2021-2026.