SCROLL NEWS / DISCOVERY
Search headlines
Find the stories shaping the conversation.
Results for " hub " 7,086 found 🔀 AI-powered Shuffle
The Big Holes in Wearable Heart Rate Variability And Readiness Scores
On September 9th, Apple announced it was revamping its Apple Watch Health Sensing System, rolling out a Readiness score (0 to 10), and increasing the frequency of heart rate variability (HRV) outputs 24-fold. This can be viewed as upping its competition with various other consumer wearable sensors. These “readiness scores” as a composite of multiple metrics, with heart rate variability (HRV) being front and center for most. The majority of Americans are now using wearable sensors, which equates to well over 100 million adults. HRV and Readiness scores are increasingly being marketed as a measurement of autonomic nervous system health, a digital marker for future disease, a clock for biological age, and a holistic metric to promote healthspan and even longevity. (Apple also introduced a new longevity tab and “Health Age”.) None of this has been proven. In this edition of Ground Truths I am going to review what we know about heart rate variability and readiness scores. Heart Rate Variability HRV is the variation in normal heart cycle timing. The variability of the heart rate, the barely perceptible millisecond changes in time between consecutive heart beats (see R-R intervals in the Figure below, left panel), is due to interplay between the sympathetic and parasympathetic (vagal nerve) inputs. Distinct from heart rate, individuals with the same heart rate can have very different HRVs. It is a rough reflection of the autonomic nervous system (ANS) activity, inadequate to say whether a person’s ANS function is abnormal. For more than three decades, heart rate variability (HRV) has been measured and several studies have found an association of low HRV and clinical outcomes, particularly a link with higher all-cause and cardiovascular mortality. There have also been less well established links of low HRV to risk of early cognitive impairment, dementia, mental illness, Type 2 diabetes and substance abuse. An important reminder is that HRV is a surrogate marker without any established cause-and-effect relationship. If you increase your HRV, that doesn’t mean it will improve health outcomes. In fact, there is no hard evidence for that. All that work linking to health outcomes was done with electrocardiogram (ECG) derived HRV. Now, in the era of consumer wearables, this is getting assessed differently, by optical pulse (yes, the lights you see) plethysmography (PPG) or what is called pulse rate variability (PRV). They are not the same, as shown below (right panel) and only concordant when the delay between the ECG and pulse is kept constant, which basically means at rest. I should mention there’s also what I will call MPV, a mattress mechanical movement sensor, a derived heart rate variability, that companies like Eight Sleep use, even further away from directly measuring HRV. HRV has not one uniform measurement but many different types of quantification, such as RMSSD, the magnitude of difference between successive R-R intervals of normal sinus beats (N-N) or SDNN, the standard deviation of NN intervals, both in milliseconds. SDNN is one of the so-called frequency domain HRVs (others are LF, HF, LF/HF). Different wearable sensors use different metics; Apple has relied on SDNN and nearly all of the others use RMSSD, which is generally considered the more accurate metric. There’s also the different length of time measured, such as for a matter of minutes, all day, or an overnight’s sleep. Short measurements are especially problematic since they don’t capture enough of respiratory modulation and other factors that influence HRV. Share Ground Truths How well does HRV correlate with PRV? There are very limited studies, especially independently done. One that is commonly cited was conducted by Air Force researchers in only 13 healthy adults assessing Oura ring 3 and 4, Whoop 4.0, and Garmin Fenix 6 and showed a correlation coefficient of 0.88 to 0.97 and a mean absolute percentage error from 6 to 10%. The correlation is not a perfect 1.0, but there’s at least a fairly high level of correlation. HRV is supposed to increase during the night due to takeover of the parasympathetic nervous system, and higher during deep sleep. A recent example of my 1 week, all day “HRV,” and one during sleep is shown below. As you can see, the N of 1 data are inconsistent for the same days from different sensors (Oura, AppleWatch, Fitbit Air, and Eight Sleep) by patterns, absolute numbers, and comparison with prior days and weeks. The largest study in over 8 million Fitbit users (the old version, not Google Fitbit Air, introduced in May 2026) gives you a sense of the effect of age, sex, and the 2 different main HRV (here PRV) metrics, with RMSSD on the left and SDRR (=SDNN) on the right below. That study, from data collected in 2018, is a major outlier, since all the more recent ones are tiny with respect to sample size. Many of the companies have not had independent evaluation of their HRV, such as Eight Sleep, but have published a low standard error on their website. There are some other published studies on the correlation between HRV and PRV, but they are all small and only in healthy adults. A scoping review emphasized the lack of study in underrepresented individuals, including the aged, people of color (which affects the PPG signal), and individuals who are underweight or obese. Add the typical adult age 60 plus with one or more chronic diseases. For example, one study in over 900 adults found poor correlation of HRV and PRV, non-uniformly underestimated across many chronic diseases (cardiovascular, endocrine, neurological, respiratory, and others), concluding PRV is “an invalid surrogate for HRV.” A recent systematic review of 43 studies comparing HRV and PRV found reasonable pooled absolute standardized error (HRV as gold standard) but only 10 of the studies provided quantitative synthesis in ideal conditions. Their main conclusion was similarly cautious: “PPG-derived HRV [PRV] should not be regarded as universally interchangeable with ECG-derived HRV across all devices, populations, and recording contexts.” Factors Affecting HRV and PRV That gets me to the long list of factors that affect HRV (and PRV) besides the device, the type of measurement (RMSSD, SDNN or others), the person’s signal, the sensor site, the duration of data capture, if weighting by sleep stage is used, how artifact is processed and corrected. And this list is not complete!: Oura puts out data from their community of users (who input data) on what affects their overnight HRV. The factors currently provided are: no alcohol (increase 8%), melatonin (increase 2%, float tank (increase 2%), wine (decrease 4%), and party (decrease 14%) in overnight HRV. Must be some big parties! Subscribe What is a PRV measurement good for? It has been falsely characterized as an index of “autonomic balance” and a specific indicator of stress. A 2018 review of the studies available for HRV and its relationship to stress, not using any of the current wearables, found that stress can lower HRV. But so can many other factors. The non-specificity of the signal, indexed to the table above, is striking. Evidence from a UK Biobank study of over 46,000 participants with actual HRV looked at genetically predicted HRV, a genetic risk score, that failed to show the expected HRV-mortality link, indicating that _HRV is likely not causa_l, but rather a reflection of person’s physiologic state. A review of consumer wearable HRV data from 5 longitudinal studies showed that nighttime PRV was not associated with perceived stress, and surprisingly higher HRV, in the largest cohort (N=717 participants), was correlated with higher stress. An Oura ring cohort of 525 first-year college students found a link between overnight PRV and perceived stress, but that was also seen with resting heart rate, sleep, and respiratory rate. Several very small studies have examined the relationship of HRV and athletic injuries or guiding training with mixed, and predominantly negative results. HRV biofeedback training with paced breathing had no significant effect on reducing stress or raising HRV, as demonstrated with sham controlled trials. When HRV for multiple days showed a decline in conjunction with body temperature, the Oura ring published data for prediction of Covid. The WHOOP company sponsored an observational study, published in 2026, of 30,000 users for 72 weeks, without a control group, that reported reduced alcohol intake (5.8 % points) by self-report. That doesn’t tell us much, and particularly about the merits of HRV for behavioral change. If you use the same device and conditions as longitudinal trends for multiple (at least 2-3) weeks that may be the one way to get something useful from the measurements. Data for overnight sleep with minimal motion and using RMSSD is the best proxy for real HRV. The reason to look at trends rather than any given night is that it more likely represents something, even though you won’t know with certainty what the “it” is. Keep in mind there are no data, no peer-reviewed evidence, to show that HRV fluctuation in-person has any correlation with health outcomes. Share Readiness Scores These are proprietary scores that integrate different metrics for each of the wearables: no algorithms have been disclosed. They are unvalidated against health outcomes. In a review of 14 composite health scores of readiness and recovery, HRV contributed 86% to the scores, followed by reading heart rate (79%), physical activity and sleep duration (both at 71%). That review noted the substantial variability in measurement protools and lack of standardization. Sleep staging is notoriously inconsistent and inaccurate by these sensors, which adds further to the HRV uncertainties for what the scores, which use sleep stage data, mean. Only resting heart rate has been shown consistently across devices to be extremely accurate. I’ve made a Table to summarize what we know about which metrics are included, the scores, any peer-reviewed studies that compared the readiness score with health outcomes, and the corresponding (if any, NA-not available) citation. You will note that some companies do not use the term “readiness," such as WHOOP for recovery, and Garmin, which has 2 different scores, one of which is Body Battery. Eight Sleep uses the term “Fitness Score.” They all include HRV; Apple includes a new metric they call “Recovery HRV” which among other components uses 7-days of sleep, but it is unclear what this means or how it is differentiated from other scores (there are clearly no data for outcomes). We have no knowledge of how the different components are weighted or whether any of these scores are better than resting heart rate, HRV alone, physical activity, or any other single metric. Since none of these are standardized, they are not interchangeable, so if you get a 90 for Oura that has no relationship to a 90 on a Google Fitbit Air. Notably, the company can update its algorithm for readiness score at any point without notification to device users. Without any useful evidence of actionability for these scores or established relationship with health outcomes, it is hard to make a case for their value. At the Apple recent announcement they showed their Readiness score (0-10) on the watch (Figure below) but there are no published data on this score, not even on their website. It’s available only on their new Watch Series 12 or Ultra 4 [of course, ;-)]. That exemplifies the problems with these scores, lack of data and evidence for being meaningful to promote health. Perhaps the best study (which isn’t saying much) is the WHOOP Recovery for golfer performance, because it did correlate with an objective outcome, even though there was no control group and the authors were all from the company. Among the 389 pro golfers, an absolute 10-per cent point increase in Recovery score was associated with about 0.5 fewer strokes per round. But that’s hardly a health outcome! WHOOP is also conducting a study in over 2,700 runners to see if their recovery score will be linked to less injuries and improved performance, but that is not yet published and has no control group or randomization. Putting This in Context For two decades I’ve been enthusiastic about the potential for digital health and particularly wearable biosensors. Over the years, we’ve seen some great progress for their ability to promote physical activity and accurately detect atrial fibrillation (the first FDA cleared deep learning AI for consumers). That work was the subject of rigorous research. But there are holes in the data and evidence for other metrics. One notable one is the “VO2 max” story that I wrote about earlier this year. At that time many subscribers asked me to cover heart rate variability, which I finally got to here. When I dived into the research and publication for HRV and readiness scores, I expected to find at least some that were of high quality and demonstrated their utility by linkage to health outcomes. To my surprise, I found none. The wearable sensor measurements for HRV (PRV) are, for the most part, accurate, but that validation work has only been done in small studies of healthy adults and does not take into account the long list of factors, from the device, software side, and the user side, that affect HRV measurements. Moreover, this metric chiefly relies on optical sensing and, as we have learned for heart rate PPG sensing, may be less accurate in people of color. Keep in mind that all of the health outcome association evidence comes from ECG-derived HRV; none are from wearable sensor data. I will repeat the key point: there's no peer-reviewed evidence to show that in-person HRV fluctuation—or efforts to raise your HRV— has any correlation with health outcomes. For those of you who look at your HRV on awakening, or even 2+ week trends of it being low, I hope this context helps to relieve any anxiety. Yes, low HRV (not PRV) has been shown to increase risk of some diseases as summarized above. But efforts to raise your HRV—a surrogate metric— has not been established for improving any health outcomes. HRV does not have any evidence of causality (the genetic evidence actually goes against this possibility). In this summary, I have not included data for other wearable sensors such as Polar, Samsung, Withings, Suunto, Amazfit, Coros, Ultrahuman, or additional mattress sensors. These are beyond my first-hand experience, and as far as I know from my in-depth review none have any peer-reviewed published data that differ from the 6 sensors I’ve reviewed here. From the points I’ve gone over above, we’re not ready for readiness scores. Besides being proprietary, they are predominantly based on metrics that have their own issues. It’s compounding the problem, like building a house without a solid foundation that has never undergone a rigorous inspection, and then selling it. Like I mentioned for PRV, you can look at trends over weeks rather than any single day, to get a handle, but even that may not be helpful. There’s simply no evidence that these scores meaningfully relate to health outcomes. I’d emphasize they might, but that requires doing prospective or randomized studies to prove it. None exist. There’s great promise for HRV/PRV utility_. For example**,**_ Prof Maiken Nedergaard, who discovered the brain glymphatics that are essential in eliminating metabolic waste products from the brain during sleep, has posited that HRV could be a non-invasive marker for neuromodulator oscillations, brain-body regulatory circuits, and brain clearance. That would be extremely useful, but like everything else on HRV and readiness scores it requires solid research and validation. The lay media isn’t helping much to get the story straight. Earlier this year The Economist published a piece entitled “The most useful indicator of your overall health” which ordained HRV as an “accumulated stress score.” That’s akin to the false assertion about VO2max: “V02 max is the singular most powerful marker for longevity.” As I’ve summarized here, that is not established. The fact is that so many things can lower HRV, including physical exercise (especially an intense workout), reduced sleep quality, stress, the list above, no less the device, signal, and software. Whatever fluctuations observed have not been correlated with any health outcome. Sadly, “datamaxxers” are widely using HRV and readiness scores that have never been validated to mean anything. We already know that for some people using the sensors for sleep metrics, it can induce “orthosomnia,” an obsession to get high sleep quality, with associated high levels of anxiety. In an experiment done by a company to promote sleep quality for its employees, “For those employees who did use the trackers, many reported feeling perfectly rested until their tracker told them they had had a terrible night. Others were told that they had slept like a baby when they had actually been lying awake worrying about the quality of their sleep. “ The same problem can result from preoccupation with HRV or readiness scores, with anxiety that would lead to further reduction in both. It you are using a wearable like >100 million American adults, it’s OK to look at these data, but contextualized with the major caveats reviewed here. If you are one to require evidence that HRV or readiness scores are linked to health outcomes, you may not even want to look. The companies make it hard to turn them off! Let me end with the companies that make and sell wearables. Apple’s doubling down on HRV (24-fold more reporting and heart rate very 5 seconds) and introduction of a Readiness score tells us that consumers have bought into these metrics and they are joining the club. However, all of this is occurring with a backdrop of tens millions of users, claims about the data that are not backed up by adequate evidence, marketing way out in front of whatever limited data exists, and not being transparent about their readiness score algorithms. The companies can well afford to do the research that is needed to connect these metrics with health outcomes show, once and for all, that increasing HRV or using readiness scores promotes our health. If they believed and invested in the products they are selling, we’d not be in this position of not knowing. That’s essentially where we are with HRV and readiness scores. Perhaps someday this will change and we’ll have good reason to embrace them. NB: I wrote this post. No AI. I have no conflicts of interest with any of its content. Loading... Ground Truths has 215,000 subscribers from every US state and 214 countries. There are over 300,000 followers of Ground Truths so more than 90,000 folks who can easily convert to be free subscribers. Your subscription to these free essays and podcasts makes my work in putting them together worthwhile. If you’re not a subscriber, please join! If you found this interesting PLEASE share it! Share Ground Truths The proceeds from all voluntary paid subscriptions go to support our summer internship program. It enabled us to accept and support a record number of 62 summer interns that joined us in 2026! These are high school, college and medical students selected from thousands of applicants. We couldn’t do this expanded program without the funds coming in through Ground Truths. Thank you!
Nigerian-Canadian NBA executive backs $294 million sports and entertainment hub in Nairobi
A sports and entertainment investment group backed by Nigerian-Canadian NBA executive Masai Ujiri and Helios Sports & Entertainment Group is developing a $294 million multipurpose arena and entertainment district in Nairobi, as Kenya seeks to position its capital as a major destination for global events
New Hanover's 17-year life expectancy divide fuels Hub's reporting
New Hanover County has a 17 year life expectancy gap. Local journalists are working together to find out why.
Small business owner in Colorado struggles with record diesel prices, energy inflation
Political Updates: Marx could be fined $420,000, key ballot measure could be in danger
How a Minneapolis clinic helped bring healthcare to patients during Operation Metro Surge
Operation Metro Surge took a toll on schools, businesses, restaurants and medical care. Inspire Change Clinic in south Minneapolis responded by changing how it delivered care.
Colorado small business owner struggles with record diesel prices and energy inflation: "Prices are exorbitant"
With diesel prices nearly doubling, businesses that rely on diesel are hurting.
Political ad attacking CD8 candidate Manny Rutinel gets a Reality Check
Suspects smash car into business in Broomfield, steal vapes worth $5,000
Amid Ed Sheeran controversy, Philadelphia DJ Patty Jackson says it's "a new era" for music, politics
Baltimore businesses hoping to win big with Ravens and Orioles in town for back-to-back home games
Xavier Taylor's father shares health update 4 months after freak baseball injury: "He hears us"
Baltimore businesses hoping to win big with Ravens and Orioles in town for back-to-back home games
Thousands of Ravens and Orioles fans are expected to soar into downtown Baltimore, which means a big boost for local businesses.
NCDOA holds series of forum for minority small business owners after elimination of HUB in budget
Following its elimination in the new state budget, minority businesses will no longer have the aid of the Office for Historically Underutilized Businesses, which helped provide assistance with state contracts for more than 25 years.
NCDOA holds series of forum for minority small business owners after elimination of HUB in budget
Following its elimination in the new state budget, minority businesses will no longer have the aid of the Office for Historically Underutilized Businesses, which helped provide assistance with state contracts for more than 25 years.
Colorado health officials warn of possible measles exposure in Denver, Steamboat Springs
Officials from the Colorado Department of Public Health and Environment issued an alert about a possible measles exposure after a confirmed case with an unvaccinated out-of-state visitor earlier this week.
Book excerpt: "Go and Do Likewise" by Andy Beshear
The Democratic Governor of Kentucky writes about how the language of faith, which he believes has been co-opted by some politicians, can be used to bridge the nation's partisan divide.
Gov. Pritzker Launches Illinois Reproductive Health Care Hub
New website centralizes resources for reproductive care in Illinois, connecting site visitors to medical providers, affordable care options, and helpful information
ResearchHub: An Answer to “Dysfunction” in Traditional Science Giving?
The platform, cofounded by cryptocurrency billionaire and philanthropy critic Brian Armstrong, aims to eliminate counterproductive incentives that scientists face in traditional grant seeking.
Arlington officer kills man armed with knife during mental health call, police say
Engrams Embedding Entendre: Codesign for Efficient DRAM/SSD Offloading
Engram extends standard token embeddings with learned multi-token lookups. Recurring local patterns retrieve vectors directly, reducing the need to reconstruct them through attention and feed-forward layers. With Engram model architecture optimization, it allows for lower HBM capacity to be needed for models at the same quality. This does not mean there won’t be an insane demand for HBM but it just means that model architecture will continue to innovate around constraints. This model architecture design is naturally codesigned for parameter offloading: each token accesses a few embedding rows whose addresses depend on token IDs, not hidden states. The runtime can prefetch those rows from host DRAM while earlier layers compute, keeping the table outside HBM without transferring entire weight matrices. Our Memory model contains our latest estimates of quarter by quarter HBM, DRAM, & NAND supply and demand. Offloading frees HBM for model weights and KV cache, potentially supporting larger batches or more concurrent sessions. When DRAM becomes the next constraint, NVMe offers another tier. Recommendation systems already cache frequently or recently accessed embedding rows in faster memory while backing colder rows with SSDs. After NVIDIA roadmap had to change due to massively despec’ing Rubin Ultra from 1024GB to now ~200GB of HBM per chip, model architecture optimizations like emgram maybe helpful. Our DeepSeek-V4.1-Flash configuration uses roughly 189 GiB of memory for Engram. We replace it with a memory-mapped (mmap) file and measure serving performance with offload to SSD. Later on in our report, we will show our Engram offloading experiments along with the official InferenceX agentic inference serving results on Engram models like DeepSeekv4.1 Flash across all 6 NVIDIA GPU SKUs along with MI355X. Unsurprisingly, the CUDA Moat is still mogging MI355X on the ultra popular DeepSeekV4.1 Flash model. We also show how even on high capacity HBM SKUs, offloading emgrams to DRAM could result in even better performance for most of the pareto than keeping the emgram in HBM. Our benchmark has been widely reproduced, validated and/or supported by almost every major buyer of compute from Google Cloud to Microsoft Azure to Oracle, to Meta and many more. Furthermore, it has the support of the ML community including from vLLM, LMCache, SGLang, PyTorch, Huggingface and the support of major labs like OpenAI, MiniMax, ZAI, Qwen, Moonshot Kimi, etc. Star the InferenceX GitHub repository if you find the open-source benchmark and data useful!. InferenceX is the only inference benchmark in the world to have TPUv7, Jalapeño, Nvidia Rubin NVL72, AMD, and soon, SambaNova and Trainium. Due to how realistic AgentX scenario is to real world agentic inference workloads, AMD has committed to collaborating on MI455X UALoE72 too. DeepSeek did not release the original paper’s two trained Engram models. We replicated its setup on fineweb-edu using the released code and training hyperparameters, at an estimated 6E18 FLOPs per run. We observed the same U-shape scaling: Engram improved performance over pure MoE baselines. We also reproduced DeepSeek’s results, where earlier-layer representations with Engram resembled those of later layers. Like the original Engram paper, it is possible to probe Engram’s gate scores to see what n-grams DeepSeek-V4.1-Flash makes the most use of. Our gate scan finds names, code fragments, relational phrasing, and boilerplate. These examples prioritize interesting-ness over gate strength. One unexpected result was Wright : Ace Attorney. These examples suggest learned memory optimizes the training objective, not a judgment of which facts deserve storage. Licenses, bibliography fragments, API scaffolding, and website furniture can provide prediction shortcuts, so the value of additional Engram capacity may depend on what survives data preparation. This does not show that table capacity is “wasted”: the evaluation-corpus scan establishes neither training exposure nor the capacity occupied by each category. For offloading, strong gates do not identify cache-hot rows. Low gates do not automatically save reads either: computing the gate requires the retrieved key and undoes the performance gain of a fused kernel. Skipping reads would require a separate usefulness predictor before retrieval. In the original paper’s inference-time ablation, factual-knowledge benchmarks retained just 29–44% of their original performance, while reading comprehension retained 81–93%. This is due to the training–inference mismatch. The resulting degradation therefore measures this trained model’s dependence on Engram, not the performance difference between models trained with and without it. In our ablations, suppressing Engram worsens token likelihood across all evaluated domains, especially encyclopedia text and several code corpora. Surprisingly, GSM8K accuracy stays within measured run-to-run variation and removing Engram has no effect. Engram is not a detachable dictionary beside an unchanged MoE. Removing it changes downstream features and expert selection. We tested whether rerouting hurts or compensates by holding tokens fixed in a teacher-forced experiment on CRUXEval, a code-reasoning benchmark of small Python functions where the model predicts a function’s output from its code and an input, and scoring the reference answer. Removing Engram raised answer loss from 0.2848 to 0.3093 bits/token. Forcing the ablated model to use the original Engram-on expert choices made it worse still, at 0.3375 bits/token. Rerouting partially compensates for the missing memory. Memory features and expert selection work together, rather than following a clean “memory stores facts; experts reason” division. On the same CRUXeval, removing Engram during either phase reduced accuracy and increased generated tokens; removing it throughout produced the largest changes. Keeping Engram for prefill leads to more correct answers than keeping for decode likely due to semantically richer KV cache transferred to decode workers, allowing it to mitigate some of the performance loss. Engram’s table is large, but each lookup is small. DeepSeek-V4.1-Flash requests 24 rows at each of two Engram layers, about 12.4 KiB per processed token position across the model, or 3.1 KiB per GPU when split across four GPUs. Currently as of Day 7 since Model Release, MI355X is still 2-4x worse performance per dollar compared to B200 even when normalized by Mi355X’s lower TCO. Our full total cost of ownership breakdown comes from our AI Cloud TCO Model along with monthly market surveys of over 100+ gpu clouds & gpu cloud customers. On the Day 0 release of DeepSeekv4.1 Flash, NVIDIA vLLM works out of the box with zero issues across all 6 SKUs: H100, H200, B200, B300, GB200, GB300! This was thanks to the amazing work by the NVIDIA & Interact teams! In comparison, AMD vLLM did not work on day 0 for DeepSeekv4.1 Flash.Source: SemiAnalysis InferenceX AMD’s vLLM documentation points to using vllm/vllm-openai-rocm:deepseekv41-flash-0909, but from hour 0 of the model release to hour 23, AMD has not publicly released the image. AMD claims, “SPEED IS THE MOAT,” yet it has still not released it by the 23rd hour. We wish that, going forward, the AMD team has a better process for hour 0 model releases. Eventually when they did publicly release for “day 0” image support, performance-wise, it is currently up to 14.8x worse perf per dollar than H200 and up to 42x worse perf per dollar than B200/B300. The power of the CUDA MOAT is NVIDIA’s collaboration with its massive 6 million-developer community ecosystem including most of the vLLM & SGLang & Tokenspeed maintainers which means that CUDA is optimized on day 0. Overall, AMD did make significant improvements but the performance per dollar is still currently 2-4x worse than B200. AgentX Engram DRAM Offloading Improving Performance The HBM and DRAM offload use the same GPU kernel to select and dequantize rows. With HBM, it reads GPU memory; with Unified Virtual Addressing (UVA), it reads pinned host memory directly. Both support full decode graphs. Moving the table into HBM accelerates only the sparse lookup, leaving decoder computation and communication unchanged, resulting in little overall benefit while consuming memory otherwise available to KV cache. Another benefit of Engram offloaded to DRAM which means you can reduce the communication overhead by using less HBM GPUs per replica. For example, when enabling Engram offloading on B300, we are able to switch from TP4 to now TP2 which improves the pareto curve by up to 1.6x. When iso-model quality, less HBM is required as the engrams could be offloaded to host DRAM. Thus HBM bandwidth matters way more than HBM capacity. For inference workloads where memory bandwidth matters the most, 4-hi HBM provides the best $/bandwidth and therefore lowest cost per token. If China continues to make more and more revolutionary model architecture innovations, soon it could potentially 0Hi HBM stacks. [ ](https://newsletter.semianalysis.com/p/long-live-the-short-king-why-4-hi) [ Long Live the Short King: Why 4-hi HBM Wins ](https://newsletter.semianalysis.com/p/long-live-the-short-king-why-4-hi) Myron Xie, Bryan Shan, and 3 others · Sep 13 [ Read full story ](https://newsletter.semianalysis.com/p/long-live-the-short-king-why-4-hi) Moreover, on B300 and week-0 stack, moving the Engram table back to HBM did not improve results and stay within run-to-run variance. This is a result of the work optimizing DRAM offload, such as async, and overlap. SSD Offloading On B200, we created a unoptimized vLLM fork and stored the Engram tables in memory-mapped files on local SSDs. File backing lets the OS reclaim table pages when other applications need RAM. Pages already cached in memory can be served without reading the SSD again. Furthermore, note that we were unable to turn on GDS The unoptimized SSD implementation changes how rows reach the GPU. It copies row IDs to the CPU, deduplicates them, gathers the requested rows into pinned buffers, copies those rows back to the GPU and dequantizes them. This work runs between segments of the GPU execution graph. Native UVA performs row selection and dequantization directly on the GPU, avoiding the CPU round trip. A warm filesystem cache removes physical SSD reads, but leaves the coordination, row gathering and transfers. This is why a file already cached in RAM can still perform worse than a pinned DRAM table. The comparison measures the whole serving path; it does not separate the time spent on each of these operations. B200 DRAM dominates both measured SSD serving curves in total tokens per dollar and P90 interactivity. Near 125 tokens/s/user, DRAM delivers 121 million total tokens per dollar versus 52 million for SSD. For production serving, SSD offloading is likely not worth the tradeoff. On the B200 configurations we measured, SSD offloading loses on both measures: every observed SSD point has a DRAM alternative that delivers higher P90 interactivity and more total tokens per dollar. The only points where Cheaper storage does not automatically produce a cheaper inference service. Moving Engram to SSD leaves the same four expensive GPUs and the rest of the server in place. Reclaiming RAM only creates an economic benefit if it enables a cheaper server configuration or additional useful capacity. The current unoptimized path provides neither benefit, and the filesystem cache still consumes RAM when table pages are resident. Next we will look at the mechanisms and specific implementation of ngrams from DeepSeekv4.1 Flash, LongCat, Qwen3.8 Flash Next.
NASA’s Hubble Spots an Out-of-Sync Galaxy
Though the spiral galaxy in this new image from the NASA/ESA Hubble Space Telescope seems serene, it hides a chaotic secret. This galaxy is NGC
Burglary suspects smash car into Colorado business, steal vapes and merchandise worth $5,000
Reality TV star Porsha Williams reveals she had to undergo emergency partial hysterectomy: "It all happened so fast"
Porsha Williams revealed to "CBS Mornings" co-anchor Gayle King that she had to undergo an emergency partial hysterectomy this year after doctors discovered 21 uterine fibroids
Burglary suspects smash car into Broomfield business, steal vapes worth $5,000
Weekend Gardener: 2026 Texas A&M Department of Horticultural Sciences Field Day
Community members are invited to learn more about the research being done in the Texas A&M Department of Horticultural Sciences Department.
The Clicks Communicator Ships in December With More RAM and New Mobile Service
A new video shows off the BlackBerry-like phone's features, including the speech-to-text Prompt Key, Message Hub and new Clicks Mobile wireless service.
Billions at stake as Texas reshapes business contract program
Texas has dramatically overhauled its Historically Underutilized Business (HUB) program in the past year, shifting eligibility toward service-disabled veterans and leaving thousands of minority- an…
Farmer who voted for Trump says "I can't stay in business" amid rising costs
Maryland Gov. Wes Moore seeks federal aid for businesses impacted by Empire Towers emergency
Possible measles exposure reported at Children's Hospital of Philadelphia, health officials say
Health officials in Philadelphia are warning about possible measles exposures in the CHOP NICU.
This plus-size clothing business faced a $90,000 bill because of tariffs. Then the community came together to help
Dr. James Q. Simmons tackles everyday medical concerns in “What the Health”
Trump ordered DOJ not to appeal ruling that loosened limits on "gangster weapons," sources say
President Trump ordered the Justice Department not to appeal a court ruling that loosened restrictions on firearms known as "gangster weapons," sources familiar with the matter told CBS News.
When considering mental health, it's important to be aware of side effects of psychedelics
Gov. Moore requests federal assistance for Empire Towers businesses
Twin Cities gas prices surge 15 cents overnight as business owners feel the pinch
1 in 3 Americans with health insurance have medical debt, survey finds
E-bike, scooter injuries among children are a public health crisis, doctors on Long Island say
NSF invests in translating low-dimensional semiconductor technologies to establish U.S. leadership in microelectronics
The U.S. National Science Foundation today announced an initiative to translate low-dimensional semiconductor technologies from laboratory demonstrations into platforms for U.S. manufacturers to…
Clio hires former Michigan Supreme Court chief justice as GM of its judiciary business
Clio hires former Michigan Supreme Court chief justice as GM of its judiciary business
RWJBarnabas Health, Rutgers and AWS launch innovation hub
The new center gives students access to mentors from the New Jersey health system and Rutgers Robert Wood Johnson Medical School, powered by Amazon's cloud and artificial intelligence technologies.
Examining North Carolina’s Growing Latino Electorate
The analysis, which draws primarily on 2024 data available through the LPPI’s Latino Data Hub, finds that Latino eligible voters are a young and growing segment of the state’s electorate.
1 in 3 Americans with health insurance have medical debt, survey finds
Chubb Announces Leadership Appointments to Digital Business Organization
/PRNewswire/ -- Following Sean Ringsted's appointment as Chief Scientist and Executive Vice President, Chubb Group, Chubb Limited (NYSE: CB) today announced...
Sponsored Content: Better Business Bureau, CT – ignite: A New Hub for Business Growth, Collaboration & Innovation
NEW HAVEN, Conn. (WTNH) — The Better Business Bureau of Connecticut is expanding its mission beyond business reviews and consumer resources with the launch of ignite sparked by BBB, a 6,000-square-…
When DNA sounds a lasting alarm: cGAS-STING links aging to brain inflammation
Neurodegenerative diseases, cerebrovascular disorders and other age-related neurological conditions are major causes of long-term disability. A review published in SCIENCE CHINA Life Sciences by researchers from Huashan Hospital, Fudan University, examines how damaged nuclear DNA and mitochondrial DNA can become immune danger signals. The authors highlight cGAS-STING as a key molecular hub linking cellular damage, inflammaging and neuroimmune dysfunction, and discuss opportunities for more precise therapeutic intervention.
West Suburban Medical Center, Weiss Memorial now under Insight Health Systems
Two shuttered Chicago-area hospitals are under new control on Thursday morning.
West Suburban Medical Center, Weiss Memorial now under Insight Health Systems
Doral business owners say increased ICE activity is hurting business
Google Home just became a power user’s paradise
Google Home MCP opens the smart home to every AI agent; Android 17 QPR1 and One UI 9 land the same week; Trash: the 39 toll booth for your light bulbs.
Aurora Health Care 'health and wellness hub' going into closed school building in Milwaukee
A new health center is set to open next year inside a closed school building in Milwaukee.
America has more millionaires than you think. Here's how most of them got rich.
Doral mayor says city can't stop ICE operations as businesses report 70% drop in sales
Oakland small business owner looks forward to downtown revitalization effort
Oakland small business owner optimistic for downtown revitalization effort
Dreamforce conference brings another boost to downtown San Francisco businesses
Maryland health officials warn of possible measles exposure at 3 Ocean City locations
The Maryland Department of Health is warning about possible measles exposure at three locations in Ocean City earlier this month.
Luminis Health sued over alleged failure to protect patient data after cyberattack
A patient of Anne Arundel Medical Center alleges in a lawsuit that the hospital's parent company, Luminis Health, negligently failed to protect their medical information following a cybersecurity incident earlier this month, according to our media partner, The Baltimore Banner.
Celebrating Sacramento's 916 Day and looking into its impact on local business
Hubbard Homestead Park Sports Court Opens
Seattle Parks and Recreation (SPR) is happy to announce the new sports court at Hubbard Homestead Park is complete! We are celebrating with the community and our partners, One Roof Foundation, the philanthropic arm of the Seattle Kraken and Climate Pledge Arena, on Thursday, September 17 from 3 to 5 pm. Please join us at […]
Florida Democratic governor hopeful David Jolly says politics are at a "1974 post-Watergate moment"
Packers sign 320-pound defensive tackle to the practice squad
The Packers are taking a look at bolstering depth along the defensive line. According to Bill Huber of Packers on SI, the Packers have signed former Indianapolis Colts defensive tackle Eric Johnson to the practice squad. Packers Sign DL Eric Johnson Johnson, 6-foot-4 and 320 pounds, has appeared in 51 career games while producing 41 [...]
Senate Democrats meet with Abdul El-Sayed, rallying around Michigan nominee
Hubbard Hall announces Fall 2026 season
CAMBRIDGE, NY — Hubbard Hall, the renowned arts center in Washington County, anchored by its historic 1878 Opera House, announces the Fall 2026 season will open with A.R. Gurney’s Off-Broadway
House votes unanimously to hold Epstein business associate Leon Black in contempt of Congress
NSF announces 3 additional topics as part of the NSF X-Labs initiative to pursue generational breakthrough science and technology efforts
NSF X-Labs invites proposals from teams working in AI for physical systems and announces two forthcoming topics...
Introducing ‘865 Neyland’: Tennessee athletics names new entertainment district
A name has emerged for Neyland Stadium’s new entertainment district. The multi-million dollar mixed-use gathering hub at the University of Tennessee will be named “865 Neyland,” based on Knoxville’s area code — which also spells out V-O-L on the telephone keypad — and the stadium it lies beside. The development’s future address will also be...
SEC Signs Off on Finra Outside Business Reforms
Finra’s proposed rule change eliminates a reporting requirement for lower-risk side jobs and ends broker-dealer supervision of advisors’ work at unaffiliated RIAs.
BTR nears transition to an independent airport authority
The Baton Rouge Metropolitan Airport is targeting the end of October to complete its transition from city-parish governance to a stand-alone airport authority. That’s according to Louis Hubbard I… Already an INSIDER? Sign in. Already an INSIDER? Sign in
Lincoln College property to become business hub, leased for just $1
"This is an incredible opportunity for organizations to grow in a community that has so much to offer," said Uriah Kilgallin, CEO of LEAD, in a news release.
Colorado health officials warn that person with measles visited several locations
Health Foundation of South Florida Invests $225,000 to Establish Overtown Youth Center as a Community Health Access Hub
/PRNewswire/ -- The Health Foundation of South Florida today announced a $225,000 investment over three years to support the Overtown Youth Center (OYC) as it...
Georgia health care workforce shortage puts pressure on patients
Olympic gold medalist Aly Raisman on how she learned to advocate for her own health
In the latest episode of "Healthful," Olympic gold medalist Aly Raisman discusses what she's learned about speaking up for herself and taking care of her body.
Starbucks Explores Majority Stake Sale in Japan Business at Potential $3 Billion Valuation
Starbucks (NASDAQ:SBUX) is considering selling a majority stake in its Japanese operations in a transaction that could value the business at approximately $3 billion, according to two people familiar with the matter. The company has invited several financial advisers to present options for the business and is open to relinquishing majority ownership, the sources told Reuters.
Rutgers, RWJBarnabas Health launch innovation hub featuring Amazon Web Services cloud technology
Rutgers University and RWJBarnabas Health announced the launch of the Rutgers/RWJBH Innovation Hub, powered by Amazon Web Services.
Colorado science teacher hopes his Tyrannosaurus rex trackway discovery fuels ferocious passion for learning
A research associate with the Denver Museum of Nature and Science who teaches in Northglenn recently became the first person to ever identify a Tyrannosaurus rex trackway.
Students sent home after health inspector closes school cafeteria
Presidio Trust to host free wellness events in partnership with Sutter Health
Presidio Trust partners with Sutter Health to host free wellness events
Gov. Healey calls for new investments in postpartum healthcare after Lindsay Clancy trial
Scammers target Hennepin County fund meant to aid businesses impacted by ICE surge
Arc System Works are working on a brand new fighting game property as of a few months ago but it kind of slipped under the radar
Today, Automaton Media reported that for the fiscal year which ended May 2026, Arc System Works has returned to being profitable after posting a net loss in the year prior.This in itself is of course good news for the ...
Rutgers and RWJBarnabas Health to Launch Innovation Hub, Powered by Amazon Web Services
Photo: Executives from Amazon Web Services, Rutgers Robert Wood Johnson Medical School and RWJBarnabas Health gather at the AWS Imagine Summit in Chicago after announcing the launch of the Rutgers/RWJBarnabas Health Innovation Hub, powered by AWS, one of the nation’s first technology innovation hubs that brings together a medical school, academic health system and cloud[...]
