Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

We're proud to be the fastest inference provider on Artificial Analysis, OpenRouter, and Hugging Face for GLM-5.3-Flash, at 122+ TPS. All served from the US only, starting on day 0, with ZDR by default. Stay tuned for updates as our engineers continue to optimize GLM-5.3-Flash for even higher throughput... show more

Baseten

19,625 subscribers

23,114 просмотров • 1 месяц назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 14

Фото профиля badussy

badussy1 месяц назад

speed doesn't matter when you cant even use the model

Фото профиля Atri

Atri1 месяц назад

Speed is important. Cost is even more important.

Фото профиля Tofunori

Tofunori1 месяц назад

AMazing! Thank you very much!

Фото профиля Ella Tech & Tool

Ella Tech & Tool1 месяц назад

122+ TPS 🔥 Day-0 launch is wild

Фото профиля Fajar M Reza

Fajar M Reza1 месяц назад

122+ TPS matters, but geography and ZDR shape deployment choices.

Фото профиля Adam

Adam1 месяц назад

make it cheaper

Фото профиля AI Mastery Guide

AI Mastery Guide1 месяц назад

122+ TPS is genuinely impressive speed.

Фото профиля Jordan Schenck

Jordan Schenck1 месяц назад

i’m at 290 toks it’s so nice also 20k pp/s 990 in batch of 8

Фото профиля Erildo

Erildo1 месяц назад

What is ttft and your pricing ler million tokens

Фото профиля blank

blank1 месяц назад

But you don’t even accept new customers to try your inference model api’s? So

Фото профиля Tan Nguyen

Tan Nguyen1 месяц назад

Always rate limit in both openrouter and your platform…

Фото профиля Jeffrey Behnke 💻

Jeffrey Behnke 💻1 месяц назад

I was hitting higher with GLM 5.3 flash today Just a couple small sessions. P90: 193.8 tok/s P90: 239.0 tok/s

Фото профиля pccallout

pccallout1 месяц назад

fastest GLM-5.3-Flash on the planet also the only infra that treats “add credits” like Series A diligence

Фото профиля Manuel Suarez

Manuel Suarez1 месяц назад

I'm getting constant 429 on openrouter when using this, has anybody experienced this as well?

Похожие видео

Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepSeek-V4.1 Flash: 615 tok/s 1/7

Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepSeek-V4.1 Flash: 615 tok/s 1/7

RunAnywhere

64,384 просмотров • 23 дней назад

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.

Harrison Kinsley

54,330 просмотров • 23 дней назад

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Baseten

115,468 просмотров • 2 месяцев назад

For even higher throughput and lower latency: batch generation + tensor parallel with mlx-lm + and mlx.distributed. Here it's generating at 63 tok/sec (throughput) with GLM 4.7 in 6-bit and batch size 4 on 4 M3 Ultras:

For even higher throughput and lower latency: batch generation + tensor parallel with mlx-lm + and mlx.distributed. Here it's generating at 63 tok/sec (throughput) with GLM 4.7 in 6-bit and batch size 4 on 4 M3 Ultras:

Awni Hannun

22,721 просмотров • 9 месяцев назад

GLM 4.6 fans! just soared to the top as the fastest provider in Artificial Analysis for the model. > a 114 TPS and <0.18s TTFT. > That's 2x faster than the next best option on both metrics. Available now in Cline.

GLM 4.6 fans! just soared to the top as the fastest provider in Artificial Analysis for the model. > a 114 TPS and <0.18s TTFT. > That's 2x faster than the next best option on both metrics. Available now in Cline.

Cline

31,584 просмотров • 1 год назад

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

Iam_

110,563 просмотров • 1 месяц назад

glm 5.3 flash is 7.5x cheaper, but 3.4x slower than gemini 3.7 flash Z.ai glm 5.3 flash – shipped aug 26, $0.07/$0.25 per 1m Google DeepMind gemini 3.7 flash – shipped aug 13, $0.38/$1.88 per 1m we put the two models on one job: write one html file that draws an animated 3d scene in the browser. no images, no downloads, and it has to look the same on every load. the setup: three scenes – a glass aquarium in a lit room, the solar system, a night city under a thunderstorm. identical brief word for word, reasoning effort high, 64k output cap. the numbers below are not the whole run. they cover the three scenes we kept – the best one per task from each model, the ones in the video. - total generation time for the three scenes #1 gemini 3.7 flash – 10m 36s #2 glm 5.3 flash – 36m 30s - tokens spent on those three scenes #1 glm 5.3 flash – 110k #2 gemini 3.7 flash – 111k - cost of those three scenes #1 glm 5.3 flash – $0.027 #2 gemini 3.7 flash – $0.202 observations: • glm's first 10 attempts: 7 blank pages. it kept inventing short random helpers and forgetting to define one of them. the fix was one line in the brief: use exactly one random helper, named rand(), and don't invent shorthands next to it. next 12 attempts: 11 alive, 0 crashes. • glm spends 66% of its output on reasoning, gemini 57%. that is the whole speed gap. • gemini's storm came back as a black rectangle in 4 of 6 runs. glm's best storm has a branching bolt, lit rain and wet asphalt – for $0.01. conclusion: same three scenes, same token spend – glm 5.3 flash billed $0.027 and took 36m 30s, gemini 3.7 flash billed $0.202 and took 10m 36s. glm wins gemini on price and made the best storm of the whole run follow thehype. for 24/7 ai news, analysis and breakdowns

glm 5.3 flash is 7.5x cheaper, but 3.4x slower than gemini 3.7 flash Z.ai glm 5.3 flash – shipped aug 26, $0.07/$0.25 per 1m Google DeepMind gemini 3.7 flash – shipped aug 13, $0.38/$1.88 per 1m we put the two models on one job: write one html file that draws an animated 3d scene in the browser. no images, no downloads, and it has to look the same on every load. the setup: three scenes – a glass aquarium in a lit room, the solar system, a night city under a thunderstorm. identical brief word for word, reasoning effort high, 64k output cap. the numbers below are not the whole run. they cover the three scenes we kept – the best one per task from each model, the ones in the video. - total generation time for the three scenes #1 gemini 3.7 flash – 10m 36s #2 glm 5.3 flash – 36m 30s - tokens spent on those three scenes #1 glm 5.3 flash – 110k #2 gemini 3.7 flash – 111k - cost of those three scenes #1 glm 5.3 flash – $0.027 #2 gemini 3.7 flash – $0.202 observations: • glm's first 10 attempts: 7 blank pages. it kept inventing short random helpers and forgetting to define one of them. the fix was one line in the brief: use exactly one random helper, named rand(), and don't invent shorthands next to it. next 12 attempts: 11 alive, 0 crashes. • glm spends 66% of its output on reasoning, gemini 57%. that is the whole speed gap. • gemini's storm came back as a black rectangle in 4 of 6 runs. glm's best storm has a branching bolt, lit rain and wet asphalt – for $0.01. conclusion: same three scenes, same token spend – glm 5.3 flash billed $0.027 and took 36m 30s, gemini 3.7 flash billed $0.202 and took 10m 36s. glm wins gemini on price and made the best storm of the whole run follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

16,041 просмотров • 1 месяц назад

New on DigitalOcean's Inference Engine: GLM-5.3-Flash from Z.ai. Agentic coding that rivals top-tier models, now natively multimodal for browser and computer use. 1M token context, MoE architecture, one endpoint swap to try it. Senior Developer Advocate Ryan O'Connor breaks it down, and Z.ai for Startups is there to help AI startups build faster with GLM models. 👇

New on DigitalOcean's Inference Engine: GLM-5.3-Flash from Z.ai. Agentic coding that rivals top-tier models, now natively multimodal for browser and computer use. 1M token context, MoE architecture, one endpoint swap to try it. Senior Developer Advocate Ryan O'Connor breaks it down, and Z.ai for Startups is there to help AI startups build faster with GLM models. 👇

DigitalOcean

140,776 просмотров • 1 месяц назад

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

26,360 просмотров • 1 месяц назад

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in

atomic.chat

32,515 просмотров • 1 месяц назад

🚨 GLM 5.3 just dropped, and here’s how to access the GLM family completely FREE. no subscription. no API credit cost & no rate limit. step 1️⃣: download the OpenCode app on your PC. it’s available on both Mac and Windows. 🔗: step 2️⃣: go to NVIDIA’s website, sign up with your email, verify your account, and generate a unified API key for free. NVIDIA offers free model endpoints for developers, and GLM 5.2 is one of the top models currently available there. 🔗: step 3️⃣: launch OpenCode, open the model selection menu, search for NVIDIA, and paste the API key you generated. also, there’s no rate limit, but traffic to the model through NVIDIA can get busy at times, so responses may occasionally be slower or temporarily unavailable. the only catch: NVIDIA hasn’t listed GLM 5.3 yet, so for now you’ll be using GLM 5.2. once GLM 5.3 gets added to NVIDIA’s model catalog, you should be able to switch to it the same way.

🚨 GLM 5.3 just dropped, and here’s how to access the GLM family completely FREE. no subscription. no API credit cost & no rate limit. step 1️⃣: download the OpenCode app on your PC. it’s available on both Mac and Windows. 🔗: step 2️⃣: go to NVIDIA’s website, sign up with your email, verify your account, and generate a unified API key for free. NVIDIA offers free model endpoints for developers, and GLM 5.2 is one of the top models currently available there. 🔗: step 3️⃣: launch OpenCode, open the model selection menu, search for NVIDIA, and paste the API key you generated. also, there’s no rate limit, but traffic to the model through NVIDIA can get busy at times, so responses may occasionally be slower or temporarily unavailable. the only catch: NVIDIA hasn’t listed GLM 5.3 yet, so for now you’ll be using GLM 5.2. once GLM 5.3 gets added to NVIDIA’s model catalog, you should be able to switch to it the same way.

m0h

101,243 просмотров • 2 месяцев назад

deepseek v4.1 flash is now 100% free 😳 a new coding agent is using ads to keep the whole thing free. > DeepSeek V4.1 Flash > GPT 6 Luna > GLM 5.3 Flash > More model How to get start → go to [ → sign up with GitHub → generate your API key these models be used for six hours per day.

deepseek v4.1 flash is now 100% free 😳 a new coding agent is using ads to keep the whole thing free. > DeepSeek V4.1 Flash > GPT 6 Luna > GLM 5.3 Flash > More model How to get start → go to [ → sign up with GitHub → generate your API key these models be used for six hours per day.

BARIK

24,236 просмотров • 28 дней назад

Notion's AI Meeting Notes run on Baseten, and Baseten's knowledge base runs on Notion. Our teams have been working together closely to push the frontier on both fronts. For AI Meeting Notes, our voice engineers built the fastest, highest-quality, yet lowest-cost solution on the market for speaker-attributed transcripts. We're proud to partner with the Notion team.

Notion's AI Meeting Notes run on Baseten, and Baseten's knowledge base runs on Notion. Our teams have been working together closely to push the frontier on both fronts. For AI Meeting Notes, our voice engineers built the fastest, highest-quality, yet lowest-cost solution on the market for speaker-attributed transcripts. We're proud to partner with the Notion team.

Baseten

36,604 просмотров • 1 месяц назад

Stop overpaying for api tokens, do this instead 🚨 so i switched to deepseek v4 flash…free on codex/claude paired with glm 5.3 flash as subagents with antseed free. no card. no account. 200+ providers on the network. [it takes 3 mins to set up — here is how] 1. download antseed ( 2. connect codex/claude code/hermes etc 3. pick a provider, that’s it It is anonymous, happy tokenmaxxing

Stop overpaying for api tokens, do this instead 🚨 so i switched to deepseek v4 flash…free on codex/claude paired with glm 5.3 flash as subagents with antseed free. no card. no account. 200+ providers on the network. [it takes 3 mins to set up — here is how] 1. download antseed ( 2. connect codex/claude code/hermes etc 3. pick a provider, that’s it It is anonymous, happy tokenmaxxing

painn

52,176 просмотров • 8 дней назад

Local AI v6.11.2 on Omarchy is out. Look how I'm running GLM-5.3-Flash on a SINGLE RTX 3090 at exl3-3bpw What I'm doing is putting parts of the model on NVMe, parts on DDR4 RAM, and the GPU is used as a station of sorts, we send the math to be done there. I value freedom

Local AI v6.11.2 on Omarchy is out. Look how I'm running GLM-5.3-Flash on a SINGLE RTX 3090 at exl3-3bpw What I'm doing is putting parts of the model on NVMe, parts on DDR4 RAM, and the GPU is used as a station of sorts, we send the math to be done there. I value freedom

0xSero

13,338 просмотров • 7 дней назад

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively. Read more in our announcement:

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively. Read more in our announcement:

Baseten

23,432 просмотров • 5 дней назад

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.

Baseten

35,358 просмотров • 1 год назад

GLM-5.3-Flash running at up to 300 tok/s single stream, and 1000 tok/s with 8 concurrent sessions. On average it's working at 150 tok/s per stream. Phenomenal model, really something special. On 2x Sparks we get 60 tok/s and 4x 100 tok/s 300B params is the sweet spot.

GLM-5.3-Flash running at up to 300 tok/s single stream, and 1000 tok/s with 8 concurrent sessions. On average it's working at 150 tok/s per stream. Phenomenal model, really something special. On 2x Sparks we get 60 tok/s and 4x 100 tok/s 300B params is the sweet spot.

0xSero

30,628 просмотров • 1 месяц назад

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

Timothy Young

10,180 просмотров • 2 лет назад

🤯 GLM-5.3-Flash 4bit on two M5 Ultras (tp=2) with TensorFold and 4x TB5 cables bonded. 🚀 114 tks decode on Prose single stream, and ~1600tks prefil. C=8 decode up to 200tps. There is headroom here as well, but this is where we landed today. A new-session TTFT with our prefix-cache lean mode is 0.06s. Alex Ziskind Thanks for letting me use the M5Us!

🤯 GLM-5.3-Flash 4bit on two M5 Ultras (tp=2) with TensorFold and 4x TB5 cables bonded. 🚀 114 tks decode on Prose single stream, and ~1600tks prefil. C=8 decode up to 200tps. There is headroom here as well, but this is where we landed today. A new-session TTFT with our prefix-cache lean mode is 0.06s. Alex Ziskind Thanks for letting me use the M5Us!

Ash Hart

26,047 просмотров • 7 дней назад