Submissions from fireworks.ai

		Frontier RL Is Cheaper Than You Think (fireworks.ai)
		2 points by smurda 8 days ago \| past \| discuss
		Why Building Mega Clusters Is Wrong (fireworks.ai)
		2 points by smurda 13 days ago \| past \| discuss
		Deep-Dive into LLM Fine-Tuning (fireworks.ai)
		2 points by smurda 39 days ago \| past
		Turn Your LLM into a Calibrated Classifier for $2 (fireworks.ai)
		2 points by smurda 42 days ago \| past
		DPO, your simplest RL pipeline with two rollouts (fireworks.ai)
		1 point by smurda 44 days ago \| past
		Turning Production Logs into Evaluation Datasets: A Data-Driven Approach (fireworks.ai)
		1 point by smurda 46 days ago \| past
		The Benchmark Gap: What It Takes to Ship Kimi K2.5 (fireworks.ai)
		2 points by smurda 46 days ago \| past
		LLM Eval Driven Development with Claude Code (fireworks.ai)
		4 points by dphuang2 7 months ago \| past
		Natural Language → SQL with Reinforcement Fine Tuning (RFT) (fireworks.ai)
		1 point by mehzer 7 months ago \| past
		Can DeepSeek R1 Teach Better Than Humans? (fireworks.ai)
		1 point by gregorymichael on Feb 5, 2025 \| past
		Document Inlining: Crossing the Modality Gap with Compound AI (fireworks.ai)
		1 point by swyx on Dec 23, 2024 \| past
		Fireworks F1: A Breakthrough in Complex Reasoning with Compound AI (fireworks.ai)
		17 points by sunaookami on Nov 18, 2024 \| past \| 8 comments
		FireAttention V3: Enabling AMD as a Viable Alternative for GPU Inference (fireworks.ai)
		20 points by swyx on Oct 17, 2024 \| past
		FireAttention V3: Enabling AMD as a Viable Alternative for GPU Inference (fireworks.ai)
		1 point by pella on Oct 16, 2024 \| past
		How to accurately and interpretably evaluate the quant effect of large models? (fireworks.ai)
		1 point by nilv on Aug 9, 2024 \| past
		How Fireworks evaluates quantization precisely and interpretably (fireworks.ai)
		2 points by swyx on Aug 3, 2024 \| past \| 1 comment
		GPUs on-demand: Not serverless, not reserved, but some third thing (fireworks.ai)
		1 point by swyx on June 7, 2024 \| past
		Serving Open Source Models 4x faster than vLLM by quantizing with ~no tradeoffs (fireworks.ai)
		1 point by kmdupree on March 21, 2024 \| past
		FireFunction V1 – GPT-4-level function calling model – 4x faster, open weights (fireworks.ai)
		7 points by swyx on Feb 22, 2024 \| past
		How are people training this LLMs? Dont they need lot of money? (fireworks.ai)
		4 points by Robinhoodd on Jan 19, 2024 \| past \| 1 comment
		Serving Open Source Models 4x faster than vLLM by quantizing with ~no tradeoffs (fireworks.ai)
		3 points by georgehill on Jan 10, 2024 \| past
		FireAttention – Serving Mixtral and open-source MoE models at 4x speed vs. vLLM (fireworks.ai)
		3 points by raymond513 on Jan 9, 2024 \| past
		Fireworks: Function Calling Model and API (fireworks.ai)
		53 points by tosh on Dec 21, 2023 \| past \| 18 comments
		Accelerating Code Completion with Fireworks Fast LLM Inference (fireworks.ai)
		2 points by adocomplete on Oct 11, 2023 \| past
		Fireworks.ai: Language Model Serving with Custom LoRA Fine-Tuned Models (fireworks.ai)
		1 point by vfmadd on Aug 18, 2023 \| past
		Multi-Query Attention Is All You Need (fireworks.ai)
		3 points by vfmadd on July 13, 2023 \| past

HN For You