Comments URL: https://news.ycombinator.com/item?id=50034724

Points: 1

# Comments: 1

"Affected products: ... Up to (excluding) 152.0.7977.82"

.82 is fixed.

Comments URL: https://news.ycombinator.com/item?id=49568077

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49323668

Points: 3

# Comments: 0

Instructions to reproduce, and benchmarks here: https://forums.developer.nvidia.com/t/deepseek-v4-flash-offi...

But mostly I wanted to raise awareness to readers of your article that no, if you want to do inference, paying 15K for a single 96GB card almost certainly makes no sense. Buy 4 GX10s with the same money, and enjoy dramatically better models and user scalability.

Regardless - thanks for putting the effort to share your findings! I keep postponing doing the same... there's tons of things everyone is re-discovering on their own.

IMHO, the author could have done two things better:

- vllm instead of llama.cpp. With NVIDIA HW, there is huge difference in multi-user loads and caching with vllm; when he was complaining about what happens when more than one user uses the model, and about losing caching, I was "well, duh".

- The budget he used for a single card could have instead be put to far, far better use with SPARKs. I have access to a cluster of 2 x GX10 - total cost less than half what he paid, even today - and I am running vllm and Deepseek v4 Flash. The difference compared to any Qwen is tremendous - I've NEVER seen it loop, and in all my experiments so far, it's the most Sonnet-y model I've ever tried (antirez seems to agree, hence his ds4 fork).

If you're wondering about how I set it up in the 2 GX10s: https://forums.developer.nvidia.com/t/deepseek-v4-flash-offi...

Performance: 2K t/s prefill ( very useful for feeding tons of source code into its massive context window ) and around 50-60 tg/s in my coding sessions in the pi.dev harness. With the money the author paid, he could have bought 4 GX10s, and double both numbers ( vllm basically scales almost linearly with tensor parallelism ).

Comments URL: https://news.ycombinator.com/item?id=48432946

Points: 2

# Comments: 0

It's very nice seeing it put to use in actual Spectrum machines - love it :-)

Thank you so much! :-)

Comments URL: https://news.ycombinator.com/item?id=48167177

Points: 85

# Comments: 13

Comments URL: https://news.ycombinator.com/item?id=47909750

Points: 2

# Comments: 0

And for expats like me in NL, I guess this begs for getting hooked into local llama.cpp/AIs for automatic translation :-)

Comments URL: https://news.ycombinator.com/item?id=45850663

Points: 2

# Comments: 1

But I was curious for your approach... so I asked Claude to convert it to bash: https://claude.ai/public/artifacts/01a49347-1617-4afe-8476-0...

Works like a charm - pinned it to Ctrl-k, which was free in my setup. I guess I don't have to depend on XTerm for this any more :-)

Thanks!

I became so obsessed with the project that I was looking forward to tinkering with it after coming back from work every day; so it was hacked in 5 evenings and a weekend. It was that much fun, to build a Forth.

I highly recommend the process; I think the only other time I felt so enlightened was when I first met Lisp macros (https://www.thanassis.space/score4.html#lisp).

Comments URL: https://news.ycombinator.com/item?id=36368211

Points: 2

# Comments: 0

I just changed my server, and uninstalled the - now truly useless - fail2ban. I use SSH keys of course, but without fail2ban my server's logs were constantly flooded with hacking attempts.

No longer - wireguard for the win. Thank you, chlorion!

Many thanks, OP.

Comments URL: https://news.ycombinator.com/item?id=35669723

Points: 2

# Comments: 0