https://ashwanijha.dev 2026-05-21T17:09:09.612Z weekly 1 https://ashwanijha.dev/blog 2026-05-21T17:09:09.612Z daily 0.9 https://ashwanijha.dev/consulting 2026-05-21T17:09:09.612Z monthly 0.9 https://ashwanijha.dev/extremis-cloud 2026-05-21T17:09:09.612Z monthly 0.8 https://ashwanijha.dev/newsletter 2026-05-21T17:09:09.612Z monthly 0.7 https://ashwanijha.dev/blog/speculative-decoding-what-the-paper-actually-says 2026-05-21T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/how-llms-learn-to-use-tools 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/transformer-architecture-production-guide 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/teaching-llms-to-use-tools 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/self-correcting-agents-in-production 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/how-i-think-about-agent-memory 2026-05-16T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/gqa-grouped-query-attention-production 2026-05-21T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/continuous-batching-orca-what-the-paper-actually-says 2026-05-21T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/chain-of-thought-what-the-paper-actually-says 2026-05-21T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/zero-distributed-training-memory 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/speculative-decoding-production-inference 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/rlhf-instructgpt-what-the-paper-actually-says 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/pagedattention-kv-cache-memory-management 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/mixture-of-experts-production-inference 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/lora-fine-tuning-production 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/flash-attention-what-the-paper-actually-says 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/direct-preference-optimization-what-the-paper-actually-says 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/chinchilla-compute-optimal-training 2026-05-20T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/scaling-laws-production-implications 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/rag-in-production 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/mapreduce-design-decisions 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/gpt3-few-shot-learning-in-production 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/dynamo-eventual-consistency-production 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/constitutional-ai-what-the-paper-actually-says 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/bert-fine-tuning-production 2026-05-19T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/how-i-think-about-agent-observability 2026-05-16T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/agent-observability-stack 2026-05-16T00:00:00.000Z monthly 0.7 https://ashwanijha.dev/blog/building-a-brain 2026-02-20T00:00:00.000Z monthly 0.7