#mi355x — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #mi355x, aggregated by home.social.
-
RT @wafer_ai: 🚨 EILMELDUNG: Diese Ingenieure haben herausgefunden, wie sich GLM 5.2 auf der @AMD MI355X mit 2626 Token pro Sekunde pro Knoten und 213 Token pro Sekunde im Einzelstream betreiben lässt – bei über doppelt so niedrigen Kosten im Vergleich zu Blackwell, was etwa 80 % der B200-Durchsatzleistung bei über doppelt so niedrigen Kosten bedeutet. Der vollständige Artikel steht in der Antwort.
mehr auf Arint.info
#AI #AMD #CostEfficiency #GLM52 #MachineLearning #MI355X #arint_info
-
RT @wafer_ai: 🚨 EILMELDUNG: Diese Ingenieure haben herausgefunden, wie sich GLM 5.2 auf der @AMD MI355X mit 2626 Token pro Sekunde pro Knoten und 213 Token pro Sekunde im Einzelstream betreiben lässt – bei über doppelt so niedrigen Kosten im Vergleich zu Blackwell, was etwa 80 % der B200-Durchsatzleistung bei über doppelt so niedrigen Kosten bedeutet. Der vollständige Artikel steht in der Antwort.
mehr auf Arint.info
#AI #AMD #CostEfficiency #GLM52 #MachineLearning #MI355X #arint_info
-
🚀✨ WaferAnnouncing the latest #AI #jargon salad: #GLM5.2 zooming on #AMD #MI355X at a bargain-bin price! 🤑 Pay no mind to the buzzword bingo; just know it's "faster" and "cheaper." Who needs clarity when you've got an avalanche of acronyms and performance claims? 🌩️💰
https://www.wafer.ai/blog/glm52-amd #BuzzwordBingo #PerformanceClaims #HackerNews #ngated -
🚀✨ WaferAnnouncing the latest #AI #jargon salad: #GLM5.2 zooming on #AMD #MI355X at a bargain-bin price! 🤑 Pay no mind to the buzzword bingo; just know it's "faster" and "cheaper." Who needs clarity when you've got an avalanche of acronyms and performance claims? 🌩️💰
https://www.wafer.ai/blog/glm52-amd #BuzzwordBingo #PerformanceClaims #HackerNews #ngated -
GLM5.2 on AMD MI355X at 2626 tok/s/node at over 2x lower cost than Blackwell
https://www.wafer.ai/blog/glm52-amd
#HackerNews #GLM5.2 #AMD #MI355X #tok/s #Blackwell #cost-effective
-
GLM5.2 on AMD MI355X at 2626 tok/s/node at over 2x lower cost than Blackwell
https://www.wafer.ai/blog/glm52-amd
#HackerNews #GLM5.2 #AMD #MI355X #tok/s #Blackwell #cost-effective
-
Occupancy Math on the AMD MI355X: A From-First-Principles Guide
https://indianspeedster.github.io/blog/occupancy-math-mi355x/
#HackerNews #OccupancyMath #AMD #MI355X #FirstPrinciples #Guide #TechBlog
-
Occupancy Math on the AMD MI355X: A From-First-Principles Guide
https://indianspeedster.github.io/blog/occupancy-math-mi355x/
#HackerNews #OccupancyMath #AMD #MI355X #FirstPrinciples #Guide #TechBlog
-
Zyphra & AMD Launch New Open AI Platform Powered By 15MW MI355X GPUs With Expansion Planned To MI450 & Beyond Zyphra has partnered with AMD to launch its brand new open-source AI platform t...
#Featured #News #Sticky #AMD #DeepSeek #Epyc #MI355X #MI450 #MI500 #Tensorwave #Zyphra
Origin | Interest | Match -
AMD’s vLLM-ATOM Plugin Supercharges DeepSeek-R1, Kimi-K2, and gpt-oss-120B AI LLM Inference on Instinct MI350 and MI400 Accelerators AMD has introduced a new plugin called vLLM-ATOM, which superc...
#Featured #News #Sticky #AITER #AMD #FP4 #Instinct #MI350 #Instinct #MI400 #MI355X
Origin | Interest | Match -
美能源部攜手超微建10億美元AI超級電腦，應用於核能、核融合、治癌與國安等實驗
中央通訊社 2025-10-28 10:30:00 CST
美國能源部與超微（AMD）合作，將建置兩座 AI 超級電腦，以加速核能、癌症治療及國家安全等領域的科學研究。第一座系統「Lux」預計於六個月內上線。
https://www.thenewslens.com/article/260364
#Stephen Streiffer #AI晶片 #藥物研發 #Discovery #超微 #MI355X #橡樹嶺國家實驗室 #能源部 #Chris Wright #AI超級電腦 #AMD #核融合 #國防 #蘇姿丰 #核武庫 #科技 #核能 #MI430 #甲骨文 #慧與科技 #Lux #國家安全 #美國 -
#US #DepartmentOfEnergy forms $1 billion #supercomputer and #AI partnership with #AMD
US is building two machines to ensure country has enough #supercomputers to run increasingly complex experiments require harnessing enormous amounts of data-crunching capability.
#Lux to be constructed and come online within next six months will be based around AMD's #MI355X #artificialintelligence chips
#Discovery will be based around AMD's #MI430 series of chips that are tuned for #hpc
https://www.reuters.com/business/energy/us-department-energy-forms-1-billion-supercomputer-ai-partnership-with-amd-2025-10-27/ -
#US #DepartmentOfEnergy forms $1 billion #supercomputer and #AI partnership with #AMD
US is building two machines to ensure country has enough #supercomputers to run increasingly complex experiments require harnessing enormous amounts of data-crunching capability.
#Lux to be constructed and come online within next six months will be based around AMD's #MI355X #artificialintelligence chips
#Discovery will be based around AMD's #MI430 series of chips that are tuned for #hpc
https://www.reuters.com/business/energy/us-department-energy-forms-1-billion-supercomputer-ai-partnership-with-amd-2025-10-27/ -
#US #DepartmentOfEnergy forms $1 billion #supercomputer and #AI partnership with #AMD
US is building two machines to ensure country has enough #supercomputers to run increasingly complex experiments require harnessing enormous amounts of data-crunching capability.
#Lux to be constructed and come online within next six months will be based around AMD's #MI355X #artificialintelligence chips
#Discovery will be based around AMD's #MI430 series of chips that are tuned for #hpc
https://www.reuters.com/business/energy/us-department-energy-forms-1-billion-supercomputer-ai-partnership-with-amd-2025-10-27/ -
#US #DepartmentOfEnergy forms $1 billion #supercomputer and #AI partnership with #AMD
US is building two machines to ensure country has enough #supercomputers to run increasingly complex experiments require harnessing enormous amounts of data-crunching capability.
#Lux to be constructed and come online within next six months will be based around AMD's #MI355X #artificialintelligence chips
#Discovery will be based around AMD's #MI430 series of chips that are tuned for #hpc
https://www.reuters.com/business/energy/us-department-energy-forms-1-billion-supercomputer-ai-partnership-with-amd-2025-10-27/ -
#US #DepartmentOfEnergy forms $1 billion #supercomputer and #AI partnership with #AMD
US is building two machines to ensure country has enough #supercomputers to run increasingly complex experiments require harnessing enormous amounts of data-crunching capability.
#Lux to be constructed and come online within next six months will be based around AMD's #MI355X #artificialintelligence chips
#Discovery will be based around AMD's #MI430 series of chips that are tuned for #hpc
https://www.reuters.com/business/energy/us-department-energy-forms-1-billion-supercomputer-ai-partnership-with-amd-2025-10-27/ -
8x AMD Instinct #MI355X (288GB @8TB/s) take back the lead over 8x Nvidia #B200 (180GB @8TB/s) in #FluidX3D #CFD, achieving 362k MLUPs/s (vs. 219k MLUPs/s). Thanks to Jon Stevens from Hot Aisle to run the benchmarks! 🖖😊
In single-GPU, both perform about the same, but in 8x #GPU config, MI355X is 65% faster. The difference comes from PCIe bandwidth - MI355X does 55GB/s, B200 only 14GB/s. #Nvidia leaves a lot of perf on the table by not exposing #NVLink P2P to #OpenCL.
-
8x AMD Instinct #MI355X (288GB @8TB/s) take back the lead over 8x Nvidia #B200 (180GB @8TB/s) in #FluidX3D #CFD, achieving 362k MLUPs/s (vs. 219k MLUPs/s). Thanks to Jon Stevens from Hot Aisle to run the benchmarks! 🖖😊
In single-GPU, both perform about the same, but in 8x #GPU config, MI355X is 65% faster. The difference comes from PCIe bandwidth - MI355X does 55GB/s, B200 only 14GB/s. #Nvidia leaves a lot of perf on the table by not exposing #NVLink P2P to #OpenCL.
-
#AMD #ROCm 7.0 Officially Released With Many Significant Improvements
Key highlights of #ROCm7.0 include:
- AMD Instinct #MI350X and Instinct #MI355X officially supported
- #Ubuntu 24.04.3 LTS and #RockyLinux 9 with Linux 5.14 officially supported
- ROCm 7.0 supports #KVM Passthrough for MI350X and MI355X GPUs
- ROCm 7.0 supports #PyTorch 2.7, #TensorFlow 2.19.1
- Official support for Llama.cpp.
- AMD #GPU kernel driver code is now distributed separately from ROCm stack.
https://www.phoronix.com/news/AMD-ROCm-7.0-Released -
#AMD #ROCm 7.0 Officially Released With Many Significant Improvements
Key highlights of #ROCm7.0 include:
- AMD Instinct #MI350X and Instinct #MI355X officially supported
- #Ubuntu 24.04.3 LTS and #RockyLinux 9 with Linux 5.14 officially supported
- ROCm 7.0 supports #KVM Passthrough for MI350X and MI355X GPUs
- ROCm 7.0 supports #PyTorch 2.7, #TensorFlow 2.19.1
- Official support for Llama.cpp.
- AMD #GPU kernel driver code is now distributed separately from ROCm stack.
https://www.phoronix.com/news/AMD-ROCm-7.0-Released -
#AMD's Instinct #MI355X accelerator will consume 1,400 watts. #CDNA4 challenges #BlackwellUltra.
AMD's #MI350X-series #GPU are based on #CDNA 4 architecture that introduces support for FP4 and FP6 precision formats alongside FP8 and FP16.
Both SKUs will come with 288GB HBM3E memory that will offer up to 8 TB/s of bandwidth, but MI350X will offer maximum FP4/FP6 performance of 18.45 PFLOPS, whereas the MI355X is said to push the maximum FP4/FP6 performance to 20.1 PFLOPS.
https://www.tomshardware.com/pc-components/gpus/amds-instinct-mi355x-accelerator-will-consume-1-400-watts -
#AMD's Instinct #MI355X accelerator will consume 1,400 watts. #CDNA4 challenges #BlackwellUltra.
AMD's #MI350X-series #GPU are based on #CDNA 4 architecture that introduces support for FP4 and FP6 precision formats alongside FP8 and FP16.
Both SKUs will come with 288GB HBM3E memory that will offer up to 8 TB/s of bandwidth, but MI350X will offer maximum FP4/FP6 performance of 18.45 PFLOPS, whereas the MI355X is said to push the maximum FP4/FP6 performance to 20.1 PFLOPS.
https://www.tomshardware.com/pc-components/gpus/amds-instinct-mi355x-accelerator-will-consume-1-400-watts