Elation (@ObsidianLib) header
Elation (@ObsidianLib) profile picture

Elation

@ObsidianLib

Goo - a .NET declarative desktop UI framework: https://teapaw.org/t.co/gCNIM647xo SharpTUI - a lean .NET TUI Framework: https://teapaw.org/t.co/aPXnMhEFWh

Joined July 2024
  • Tweets5.5K
  • Following426
  • Followers261
544Media
Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)Photo by Elation (@ObsidianLib)
Goo speaks for itself. Cross-platform UI framework in .NET on Vulkan. OSS. Try it out :)
1
1
1
11
472
Being anti-AI is just an endless cycle of not understanding how this chart works and crying about it
Image from Elation (@ObsidianLib)
1
2
66
Hashrate on my wrist #bnt #blocknet
Image from Elation (@ObsidianLib)
4
3
1
10
227
blocknetcrypto.com/blog/2026…
Image from Blocknet Privacy (@blocknetprivacy)
12
16
5
34
3,340
🐉longhorn update🐉 #bnt #blocknet
Image from Elation (@ObsidianLib)
Image from Elation (@ObsidianLib)
2
6
235
awesome the first #blocknet block mined on the longhorn pool happened last night! Not many people on the pool yet, so it all went to one miner. If you have an AMD CPU/GPU, get in on the pool: longhornpool.net/
Image from Elation (@ObsidianLib)
1
4
7
206
LONGHORN is LIVE. longhornpool.net A #BNT #blocknet miner built for AMD, plus a zero-fee pool. Pool 0% fee Miner 2% fee The lowest total fees for AMD miners.
1
5
8
603
longhorn. soon. #bnt #blocknet
Image from Elation (@ObsidianLib)
1
1
5
274
blocknet miner specifically tuned for AMD, anyone? Long Horn 🐉😈 #bnt #blocknet
Image from Elation (@ObsidianLib)
2
4
6
707
Elation retweeted
tokate (@tokatedev) profile picture
tokate
@tokatedevOct 15
The first two gratis donations have been contributed to @_gnoland, an interpreted and fully-deterministic implementation of the Go programming language. See them here: github.com/gnolang/gno/pull/… github.com/gnolang/gno/pull/…
🤖 Made with AI
fix(gnovm): allow comma-ok results in interface variables by obselate · Pull Request #6354 ·...

fix(gnovm): allow comma-ok results in interface variables by obselate · Pull Request #6354 ·...

Fixes #6343 Use untyped bool assignability for comma-ok map indexes and type assertions. Add filetests for empty interfaces, named bools, true and false results, and incompatible targets. Update ...

github.com
2
4
44
local models take a long time to test...might as well make something to keep you mesmerized as it works.
2
82
Elation retweeted
EgorBo (@EgorBo) profile picture
EgorBo
@EgorBoOct 12
GPT + Opus (via Copilot CLI) helped me uncover 180 JIT bugs, each with a minimal C# repro using only safe code 😶 - most had been hiding from us for many releases github.com/dotnet/runtime/is…
AI bug hunting in JIT (tracking issue) · Issue #134482 · dotnet/runtime

AI bug hunting in JIT (tracking issue) · Issue #134482 · dotnet/runtime

List of issues (each with a minimal C# repro, no IL, no opt-in configs, no unsafe/UB) filed against JIT with the "AI bug hunting" script. Just so I can see the current status (how many of...

github.com
14
29
6
286
27,342
Gloop 🤝 Tern
Image from Elation (@ObsidianLib)
6
150
Elation retweeted
tokate (@tokatedev) profile picture
tokate
@tokatedevOct 12
Donating inference to your favorite OSS project will soon be beautiful and easy. Set up your repo, donate to another repo, browse issues, save profiles with your preferred harness, model, and effort. Give your inference a purpose 🌞
1
2
4
65
Bus use: stock llama.cpp reached ~145GB/s on Ornith. These engine tweaks reach ~171GB/s over a whole pass and 234GB/s in its best kernel. The memory floor for a pass is ~17.4ms, this implementation reaches 23.5ms so still some headroom left at the same quant.
2
26
Caveats: custom ggml + libllama under stock llama-server Speed moves ~2.5% run to run and more by prompt. Pooled routing changes the model, a preliminary and partial SWE-bench run showed about 11/19 resolved rate with my pi harness, 10m per task.
1
19
The takeaway so far: capacity is free but bandwidth is not. The ideal model is ~100GB of small experts behind a thin trunk, reading ~3GB per token. Ornith has the read pattern right, but does not fill the hardware's capacity.
16
Draft head: only the 65,536 most common tokens of 248k, stored at Q4_0. Used for drafts only, every token is still verified by the full Q8_0 model so the output does not change. It only moves draft acceptance rate.
1
16
Results so far, Q8_0 @ temp 1.0 32k ctx: Decode with MTP: 59.3 -> 99.7 t/s Decode without MTP: 53.1 t/s Verify pass: 33.8ms -> 23.5ms Prefill: ~1,100 t/s TTFT: 126ms short prompt, 1.5s at 1.6k tokens 37.9GB file, ~43GB loaded
1
27
Next lever is MTP and Ornith ships its own draft block. It drafts 3 tokens, then one main pass verifies 4 positions. The trunk is read once per pass, not once per token. So, a thin trunk makes verification cheap. ~2.7 tokens kept per pass.
1
24
more replies
Then the engine, a stock verify pass is ~2,400 GPU nodes and each small kernel costs about 5us. I fused them: MoE layer 42 nodes -> 1 op, linear attention layer -> 3 ops. Now 284 nodes and each weight row is read once for all 4 tokens.
1
11
There is a problem, though. 4 positions each pick 8 of 256 experts, so up to 32 expert sets per pass. The fix is pooled routing. The 4 positions share a pool of 12 experts and each takes its top 8 from the pool. ~60% less expert traffic. Routers tuned for the Strix.
1
12
Load more