Record · corpus.blog/posts/01a0f8d0-64db-722e-a9f1-3c33dfea78f3

InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper - Formerly InferenceMAX

inferencex.semianalysis.com · published 16 February 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 inferencex.semianalysis.com Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
External links: 34
Words captured: 11,719

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://github.com/SemiAnalysisAI/InferenceX

github.com

https://inferencemax.ai/

inferencemax.ai

https://inferencemax.semianalysis.com/quotes

inferencemax.semianalysis.com

https://cloud.google.com/blog/products/compute/scaling-moe-inference-with-nvidia-dynamo-on-google-cloud-a4x

cloud.google.com

https://blog.aks.azure.com/2025/10/24/dynamo-on-aks

blog.aks.azure.com

https://code.claude.com/docs/en/fast-mode

code.claude.com

https://www.cnet.com/tech/mobile/zuckerberg-move-fast-and-break-things-isnt-how-we-operate-anymore/

cnet.com

https://app.dover.com/apply/semianalysis/2a9c8da5-6d59-4ac8-8302-3877345dbce1

app.dover.com

https://x.com/vllm_project/status/2013928644302033208

x.com

https://www.linkedin.com/in/akbarnurlybayev?trk=feed-detail_main-feed-card_feed-actor-image

linkedin.com

https://en.wikipedia.org/wiki/Composability

en.wikipedia.org

https://newsletter.semianalysis.com/i/174558496/ai-total-cost-of-ownership-cost-declines

newsletter.semianalysis.com

https://blog.vllm.ai/2025/10/09/blackwell-inferencemax.html

blog.vllm.ai

https://blog.vllm.ai/2026/02/01/gpt-oss-optimizations.html

blog.vllm.ai

https://lmsys.org/blog/2025-10-14-sa-inference-max/

lmsys.org

https://github.com/ROCm/mori/tree/main

github.com

https://docs.nvidia.com/dynamo/design-docs/overall-architecture

docs.nvidia.com

https://github.com/rocm/mori

github.com

Mooncake Joins PyTorch Ecosystem Read at the source ↗

pytorch.org

https://semianalysis.com/tokenomics-model/

semianalysis.com

Cache-aware prefill–decode disaggregation (CPD) for up to 40% faster long-context LLM serving Read at the source ↗

together.ai

https://newsletter.semianalysis.com/p/nvidia-blackwell-perf-tco-analysis

newsletter.semianalysis.com

https://newsletter.semianalysis.com/i/175661150/benchmarking-the-h200-on-its-bad-hair-day

newsletter.semianalysis.com

https://inferencemax.semianalysis.com/?i_seq=8k%2F1k&g_model=DeepSeek-R1-0528&g_rundate=2026-02-12&g_runid=21928999802&i_prec=fp4%2Cfp8&i_metric=y_costh&i_log=1

inferencemax.semianalysis.com

https://lmsys.org/blog/2025-09-25-gb200-part-2/

lmsys.org

https://nvidia.github.io/TensorRT-LLM/commands/trtllm-serve/trtllm-serve.html

nvidia.github.io

https://x.com/Yuchenj_UW/status/2020214926133063705

x.com

https://semianalysis.com/ai-cloud-tco-model/

semianalysis.com

https://github.com/InferenceMAX/InferenceMAX/blob/main/perf-changelog.yaml

github.com

https://github.com/InferenceMAX/InferenceMAX/blob/main/.github/configs/nvidia-master.yaml

github.com

https://github.com/503.html

github.com

http://github.blog/changelog/2025-12-22-improved-performance-for-github-actions-workflows-page/

github.blog

https://huggingface.co/datasets/allenai/WildChat-4.8M

huggingface.co

https://newsletter.semianalysis.com/subscribe

newsletter.semianalysis.com

Elsewhere on inferencex.semianalysis.com (1)

https://inferencex.semianalysis.com/

inferencex.semianalysis.com