Record · corpus.blog/posts/01a0f8d0-64db-722e-a9f1-3c33dc752d23
AMD MI355X Qwen3.5 397B-A17B Inference: Up to 19x Throughput per GPU in 3 Months on SGLang FP8
inferencex.semianalysis.com · published 25 May 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.
0blogs citing
- First cited
- —
- Most recent
- —
- Rank this month
- not ranked
- External links
- 8
- Words captured
- 1,041
Cited by
No blog we hold has cited this post yet.
Links from this post
Link
Host
alibabacloud.com
github.com
github.com
newsletter.semianalysis.com
github.com
Elsewhere on inferencex.semianalysis.com (10)
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com
inferencex.semianalysis.com