Hackernews posts about MI400

RSS feed for MI400

01
newVibeSys Builds a Qwen3.5-397B Engine on MI300A, 2.3× Tuned SGLangsyfi.cs.washington.edu
▲ 2matt_d 28d discuss
02
newCES 2026: Taking the Lids Off AMD's Venice and MI400 SoCschipsandcheese.com
▲ 136rbanffy 304d 💬 82
03
newAMD Helios MI400 System Architecture at Hot Chips 2026www.servethehome.com
▲ 10pella 74d 💬 2
04
newAMD Says "Helios" Racks and MI400 Series GPUs on Track for 2H 2026www.nextplatform.com
▲ 4rbanffy 255d discuss
05
newAMD MI400 GPU at Hot Chips 2026www.servethehome.com
▲ 3pella 74d discuss
06
newHPE Launches AMD EPYC Venice Instinct MI400 and Nvidia Vera Rubin Compute Bladeswww.servethehome.com
▲ 3PaulHoule 348d discuss
07
newAMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 – SemiAnalysissemianalysis.com
▲ 2rbanffy 509d discuss
08
newAMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 – SemiAnalysissemianalysis.com
▲ 2rbanffy 510d discuss
09
newAMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256semianalysis.com
▲ 2pella 511d discuss
10
newHPE Launches New AMD EPYC Venice Instinct MI400 and Vera Rubin Compute Bladeswww.servethehome.com
▲ 1rbanffy 350d discuss
11
newDeepSeek V4 Flash on a Single AMD MI300Xgithub.com
▲ 382zhoutong 95d 💬 109
12
newThe AMD Radeon Instinct MI300A's Giant Memory Subsystemchipsandcheese.com
▲ 212pella 658d 💬 99
13
newBringing Up DeepSeek-V4-Flash on AMD MI300Xfergusfinn.com
▲ 120kkm 157d 💬 25
14
newAttention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guiderocm.blogs.amd.com
▲ 71matt_d 102d 💬 11
15
newExploring inference memory saturation effect: H100 vs. MI300xdstack.ai
▲ 57latchkey 701d 💬 12
16
newBoosting Computational Fluid Dynamics Performance with AMD MI300Xrocm.blogs.amd.com
▲ 47latchkey 660d 💬 45
17
newWhy isn't AMD's MI300X competitive?newsletter.semianalysis.com
▲ 46colonCapitalDee 193d 💬 36
18
newAn EPYC Exclusive for Azure: AMD's MI300C – By George Cozmachipsandcheese.com
▲ 41rbanffy 704d 💬 14
19
newNvidia wants 10Gbps HBM4 to blunt AMD's MI450, report claimswww.tomshardware.com
▲ 21rbanffy 411d discuss
20
newAttention is NOT all you need: Qwerky-72B trained using only 8 AMD MI300X GPUssubstack.recursal.ai
▲ 20jtatarchuk 584d 💬 3
21
newCross-vendor byte-identical inference for a 72B LLM (AMD MI300X vs. Nvidia H100)zenodo.org
▲ 9ashsyngh 73d discuss
22
newUsing AMD MI300X for High-Throughput, Low-Cost LLM Inferencewww.herdora.com
▲ 8technoabsurdist 482d discuss
23
newAMD 2.0 – New Sense of Urgency, MI450X Chance to Beat Nvidia, Nvidia's New Moatsemianalysis.com
▲ 7elorant 562d discuss
24
newAMD Hints at Big FP64 Increases in MI430X GPU as Ozaki Underwhelmswww.hpcwire.com
▲ 5rbanffy 237d discuss
25
newMI300X vs. H100 vs. H200 Benchmark Part 1: Trainingnewsletter.semianalysis.com
▲ 5nl 335d discuss
26
newAMD 2.0 – New Sense of Urgency| MI450X Chance to Beat Nvidia| Nvidia's New Moatsemianalysis.com
▲ 5pella 563d discuss
27
newInter-APU Communication on AMD MI300A Systems via Infinity Fabric: A Deep Divearxiv.org
▲ 4matt_d 442d discuss
28
newDeepSeek R1 inference performance: MI300X vs. H200dstack.ai
▲ 4latchkey 598d discuss
29
newSizing Up MI300A's GPUchipsandcheese.com
▲ 4klelatti 655d discuss
30
newMicrosoft beat H200 Deepseek inference with MI300techcommunity.microsoft.com
▲ 3galeos 561d 💬 1
31
newA Deep Dive into LDS Optimizations on AMD Instinct MI450 GPUsrocm.blogs.amd.com
▲ 3ks6g10 70d discuss