⠋ Sewer56 ⣠

1.8K posts

⠋ Sewer56 ⣠ banner
⠋ Sewer56 ⣠

⠋ Sewer56 ⣠

@TheSewer56

Announcements & replies only; when interesting stuff happens. Moved to sewer56 .dev @ 🦋 (app). That one person that makes a lot of fundamental modding tools

Katılım Aralık 2013
87 Takip Edilen810 Takipçiler
Andrew Feldman
Andrew Feldman@andrewdfeldman·
.@cerebras is now running Kimi K2.6 - the leading trillion parameter open source model - at ~1000 tokens per second in enterprise trials. 6.7x faster than the next-fastest GPU cloud. 10x faster than Claude Opus. 3x faster than Gemini Flash 3.5 (Google’s latest fast model). A coding task that typically takes 3 minutes finishes in under 6 seconds on Cerebras. This is what wafer scale was built for.
Andrew Feldman tweet media
English
51
51
669
48.6K
TensorWave
TensorWave@tensorwave·
You have to read this one. We just published a recap into how @wafer_ai pushed @AMD inference performance to a level that’s getting the entire ecosystem’s attention and the results are kind of wild. What makes this story interesting isn’t just the performance itself. It’s how they achieved it: systems-level optimization, smart inference tuning, and a belief that AMD can compete at the very highest tier. Proud this work was powered on TensorWave’s AMD-native cloud infrastructure and early #MI355X deployments. tensorwave.com/blog/wafer-rea…
TensorWave tweet media
English
5
6
40
4.3K
Cerebras
Cerebras@cerebras·
Cerebras is now running Kimi K2.6 – a trillion parameter model – in enterprise trials. At ~1,000 tokens/s, this is the fastest frontier model performance ever measured by Artificial Analysis @ArtificialAnlys.
Cerebras tweet media
English
166
313
4.2K
784.6K
Harsha Gaddipati
Harsha Gaddipati@GaddipatiHarsha·
Man the x algorithm is cooking my reach Only get 30 views instead of 50 smh
English
2
0
1
228
⠋ Sewer56 ⣠
⠋ Sewer56 ⣠@TheSewer56·
Note that the headline above is a *conservative* value, assuming smaller model size than current GPT5.5 estimate and GPUs. In practice may even be 3x that.
English
0
0
0
46
steve
steve@gpusteve·
if u can’t implement lfu cache in 30 min, ur ngmi. source: this was a screen for a 500k new grad role
English
8
12
683
92.8K
⠋ Sewer56 ⣠
⠋ Sewer56 ⣠@TheSewer56·
GLM-5 (Fast) on @FireworksAI_HQ is the fastest GLM-5 I've used so far. Pretty sure this is a hidden Easter Egg 🥚 from the folks at Fireworks 🎆, available for Fire Pass users. 110-120 TPS is one thing, but TTFT (response time) is stupid fast. Not sponsored, just impressed.
English
2
1
8
504
Sonic Racing: CrossWorlds
Sonic Racing: CrossWorlds@RaceCrossWorlds·
We are aware of the ongoing issues that players cannot access the Sonic Racing: CrossWorlds Demo for the Free Weekend period. We are currently investigating and will provide updates when available. We apologize for the inconvenience and thank you for understanding.
English
82
128
1.2K
194.3K
Z.ai
Z.ai@Zai_org·
@deepseek_ai Really impressive work! If you need a higher rate limit to keep those evals moving forward, we are definitely here to support you.
Z.ai tweet media
English
29
29
1.6K
129.9K
DeepSeek
DeepSeek@deepseek_ai·
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n
DeepSeek tweet media
English
1.6K
7.7K
45.3K
9.7M
⠋ Sewer56 ⣠
⠋ Sewer56 ⣠@TheSewer56·
@victor207755822 The folks at DeepSeek are simply built different (Speciale), I sometimes feel like. They straight release some pretty radical tech, extensive reports and even bring perf patches for SGLang day one so people can run it well. Simply incredible.
English
0
0
2
632
Deli Chen
Deli Chen@victor207755822·
DeepSeek-V3: Dec 26, 2024 DeepSeek-V4: Apr 24, 2026 484 days later, we humbly share our labor of love. As always, we stay true to long-termism and open source for all. AGI belongs to everyone. ❤️🌍 #DeepSeekV4 #AGIforEveryone #OpenSource
DeepSeek@deepseek_ai

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n

English
352
1.3K
13.1K
1M
⠋ Sewer56 ⣠
⠋ Sewer56 ⣠@TheSewer56·
@thdxr There's no LSP, ACP. MCP only via code ATM. No skill loading API. Outside of that, all the core functionality is there. From custom tools to permissions to agents to models.dev, etc. And some extra additions, e.g. tool settings per agent. Heavily optimized.
English
0
0
2
55
⠋ Sewer56 ⣠
⠋ Sewer56 ⣠@TheSewer56·
@thdxr Honestly, feel free to let it rip with mine github.com/Sewer56/llm-co… if you want to experiment. The important stuff's already there and things like agents are 99% drop-in compatible. Ready for intiial release. I just have wiki to complete next weekend.
English
1
0
2
74
dax
dax@thdxr·
team had a pretty good breakthrough for the data model behind opencode 2.0 today it's gonna be so good to built on top of and embed anywhere
English
51
11
1K
44.2K