corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a087a2-9458-72a2-a033-9815148e758c

Optimizing the LLM Inference Stack

mauriciopoppe.com · published 6 September 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at mauriciopoppe.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
45
Words captured
6,086

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://github.com/wafer-ai/gpu-perf-engineering-resources
github.com
https://brrrviz.com/
brrrviz.com
Performance Fundamentals Read at the source ↗
mauriciopoppe.com
Queuing Theory for Systems Engineers Read at the source ↗
mauriciopoppe.com
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed Read at the source ↗
openai.com
https://www.cerebras.ai/blog/how-cerebras-serves-gpt-5-6-sol-at-up-to-750-tokens-per-second
cerebras.ai
https://jax-ml.github.io/scaling-book/
jax-ml.github.io
https://blog.google/innovation-and-ai/infrastructure-and-cloud/google-cloud/eighth-generation-tpu-agentic-era/
blog.google
https://cloud.google.com/blog/products/compute/tpu-8t-and-tpu-8i-technical-deep-dive
cloud.google.com
https://jax-ml.github.io/scaling-book/inference/
jax-ml.github.io
https://www.makora.com/blog/reading-the-future-with-gemma-4
makora.com
https://kubernetes.io/docs/tasks/administer-cluster/memory-manager/
kubernetes.io
https://kubernetes.io/docs/concepts/resource-management/dynamic-resource-allocation/how-dra-works/
kubernetes.io
https://github.com/kubernetes/enhancements/blob/master/keps/sig-node/2837-pod-level-resource-spec/README.md
github.com
https://github.com/kubernetes/enhancements/tree/master/keps/sig-node/5526-pod-level-resource-managers
github.com
https://docs.nvidia.com/dynamo/dev/kubernetes/disaggregated-serving/overview
docs.nvidia.com
https://llm-d.ai/docs/architecture/advanced/disaggregation
llm-d.ai
https://vllm.ai/blog/2025-09-05-anatomy-of-vllm
vllm.ai
https://arxiv.org/abs/2309.06180
arxiv.org
https://vllm.ai/
vllm.ai
https://www.sglang.io/
sglang.io
https://www.makora.com/blog/dspark-for-glm52
makora.com
https://vllm-project.github.io/2026/07/27/k3.html
vllm-project.github.io
https://arxiv.org/abs/2510.26692
arxiv.org
https://arxiv.org/abs/2603.15031
arxiv.org
https://docs.vllm.ai/projects/speculators/en/latest/user_guide/algorithms/dspark/
docs.vllm.ai
https://llm-d.ai/docs/architecture/core/router
llm-d.ai
https://docs.nvidia.com/dynamo/dev/knowledge-base/modular-components/router/routing-concepts
docs.nvidia.com
https://llm-d.ai/docs/architecture/advanced/kv-management/prefix-cache-aware-routing
llm-d.ai
https://docs.nvidia.com/dynamo/
docs.nvidia.com
https://llm-d.ai/
llm-d.ai
https://docs.nvidia.com/dynamo/dev/knowledge-base/concepts/system-architecture/disaggregated-serving
docs.nvidia.com
https://llm-d.ai/blog/kvcache-wins-you-can-see
llm-d.ai
https://llm-d.ai/blog/sticky-until-saturated-token-aware-routing
llm-d.ai
https://docs.nvidia.com/dynamo/dev/knowledge-base/modular-components/router/configuration-and-tuning
docs.nvidia.com
The Pareto Frontier in LLM Inference Serving Read at the source ↗
mauriciopoppe.com
Benchmarking & Capacity Planning for Systems Engineers Read at the source ↗
mauriciopoppe.com
https://en.wikipedia.org/wiki/Mean_value_analysis
en.wikipedia.org
https://en.wikipedia.org/wiki/Kingman%27s_formula
en.wikipedia.org
https://www.makora.com/
makora.com
https://www.baseten.co/blog/how-we-built-the-worlds-fastest-api-for-glm-52/
baseten.co
https://artificialanalysis.ai/models/glm-5-2/providers
artificialanalysis.ai
https://www.makora.com/blog/trainium2-opt
makora.com
https://awsdocs-neuron.readthedocs-hosted.com/en/latest/vllm-neuron/docs/getting-started/setup-guide.html
awsdocs-neuron.readthedocs-hosted.com
https://www.baseten.co/
baseten.co