This has been posted a few times already, and no, it's not decompiled from real Photoshop.
871 karma · joined February 6, 2013
However, there is now a Rust codegen plugin for GCC, so even this disadvantage is now basically moot.
Rewrite all the things!
The best programmers on the planet have tried and failed with this task for 50 years now, so I don't think this is true.
The main disadvantage of Rust right now is not supporting some more obscure platforms, but because mold wouldn't support them anyway I don't see that as a problem.
Discussed on HN: https://news.ycombinator.com/item?id=49526069
Tensor parallel in llama.cpp using RCCL (disabled by default in llama.cpp for some reason). Surprisingly, for these cards HIP is actually faster than Vulkan, unlike the 9070 XT where Vulkan still wins.
ROCm nightlies do actually support these old cards, just not the ROCm stable releases.
The recent blog post from Google announcing TurboQuant does not change anything regarding RAM planning for the big labs.
TurboQuant itself is already a year old! So even smaller labs have probably seen and implemented it.
The new tensor cores, sorry, "Neural Accelerator" only really help with prompt preprocessing aka prefill, and not with token generation. Token generation is memory bound.
Hopefully the Ultra version (if it exists) has a bigger jump in memory bandwidth and maximum RAM.
Also important to have a few test cases the agent can quickly check against, it will often generate wrong code, but if that is easily detectable the agent can fix it and continue quickly.
I started out by letting it write a naive C version without intrinsic, and validated it against the PyTorch version.
Then I asked it (and two other models, Gemini 3.0 and GPT 5.1) to come up with some ideas on how to make it faster using SIMD vector instructions and write those down as markdown files.
Finally, I started the agent loop by giving Cursor those three markdown files, the naive C code and some more information on how to compile the code, and also an SSH command where it can upload the program and test it.
It then tested a few different variants, ran it on the target (RISC-V SBC, OrangePI RV2) to check if it improves runtime, and then continue from there. It did this 10 times, until it arrived at the final version.
The final code is very readable, and faster than any other library or compiler that I have found so far. I think the clear guardrails (output has to match exactly the reference output from PyTorch, performance must be better than before) makes this work very well.
The big advantage of the PCIe version is that it does not take up space on the desk and all the cables for ATX power control an inside the PC case.
Full-sized HDMI is nice, the only limitation here is 1080p resolution. 1440p or higher would allow mirroring the output on the main monitor to the NanoKVM, but this probably a weird use-case anyway.
You won't be out of work creating ggufs anytime soon :)
An alternative marketplace already exists with open-vsx.org, but these companies need to fund the creation of alternatives for the proprietary extensions (C#, C++, Python, maybe others) that can be used by all forks.
Not fully confirmed yet, but that sounds really bad. It seems like it also hits low power models like the 13900T, which would imply this isn't just a voltage issue from auto overclocking.
I am quite happy with Regolith Desktop [0] installed on top of standard Ubuntu. Gives you a nice tilling window manager based desktop without fiddling with config files for hours.
Uses i3 on X11, sway on Wayland.
No more fiddling with config files to make basics like system settings actually work under i3.
This way, you won't get the dreaded doomscroll interface, and you can also scrub through the video!
Hardware demand is so high, having GPUs idling is a massive waste, but you also want to have separation between dev, test and prod environments, so not obvious what to do.
NVIDIA got big because CUDA works on the most crappy notebook GPUs up to their most powerful chips, and AMD should do the same, but focusing their limited number of driver devs on the expensive enterprise hardware makes sense IMHO.
At the end of the day, the bottleneck is TSMC, on which all GPUs are produced right now, even the ones from Intel.
Some basic prompts, which are answered correctly most of the time by ChatGPT4:
There are 31 books in my house. I read 2 books over the weekend. How many books are still in my house?
> 29 books
Julia has three brothers, each of them has two sisters. How many sisters does Julia have?
> Three
If you place an orange below a plate in the living room, and then move the plate to the kitchen, where is the orange now?
> Under the plate in the kitchen.
So, not great.
I am not sure how much behavioral data GitHub can gather from logged in user, and how useful that is compared to the code that is there anyway. Maybe to figure out which parts of code are important? But that isn't really user-specific.
Also note that debug is enabled by default, so Phoronix tested the use-case most end users would actually run.
Looking forward to the new benchmarks, I wanted a filesystem with good snapshoting support for a long time, it's nice to easily revert a broken Nvidia driver update...