Wafer is making themselves synonymous with slop in the inference space. Exaggerated unfair comparisons in all their results, twitter hype posts with alarm emojis etc.
> $2.50/GPU-hr for the MI355X, $6.00 for the B300, and $4.25 for the B200.
These are not accurate prices for real terms. They seem to be comparing b200/b300 on-demand with some historical AMD price.
" The only problem with AMD is software support — slower kernels and less day-0 support on inference frameworks make serving frontier models on AMD a real engineering effort."
This part sounds like AI assisted setting this up and benchmarking it:
>The fix was trivially simple: zero-pad the head count 12→16, run the fast kernel, and extract the real 12 heads from the output.
I've recently used a frontier AI (ChatGPT 5.6 Sol on ultra) to set up a much smaller local model, and the performance optimizations it introduced left the model totally incoherent. (The model just repeats a single character, etc.)
When I see a line like the one I just quoted, it leaves me wondering if the setup is still coherent like a stock install of Kimi K3 on supported hardware.
Did they run any benchmarks on it to see if it is still correct?
If you do good work you should at least take the time to review the slop that details that work for slopiness. Otherwise it's hard to take it seriously. Especially the prefill section.
The B200 is being forcefully compared against something which is not gonna fit within it's memory in a single node & not much details about multi-node interconnectivity, disagg or not. As expected of a shoddy slop.
The only point it won is of cost per hour is one aggregation website for rentals, the premium a B300 commands against the $3/hr AMD chip which no provider has in abundance. Never bothered to do TCO of owning the hardware either.
> $2.50/GPU-hr for the MI355X, $6.00 for the B300, and $4.25 for the B200.
These are not accurate prices for real terms. They seem to be comparing b200/b300 on-demand with some historical AMD price.
" The only problem with AMD is software support — slower kernels and less day-0 support on inference frameworks make serving frontier models on AMD a real engineering effort."
>The fix was trivially simple: zero-pad the head count 12→16, run the fast kernel, and extract the real 12 heads from the output.
I've recently used a frontier AI (ChatGPT 5.6 Sol on ultra) to set up a much smaller local model, and the performance optimizations it introduced left the model totally incoherent. (The model just repeats a single character, etc.)
When I see a line like the one I just quoted, it leaves me wondering if the setup is still coherent like a stock install of Kimi K3 on supported hardware.
Did they run any benchmarks on it to see if it is still correct?
GPUs. 8× MI355X (TP8) B300 (TP8+DCP8)
Decode tok/s per stream 118 tok/s 172 tok/s
Peak aggregate. 952 tok/s 1,568 tok/s
Peak aggregate per GPU 119 tok/s 196 tok/s
On every row the B300 beat the MI355X
The B200 is being forcefully compared against something which is not gonna fit within it's memory in a single node & not much details about multi-node interconnectivity, disagg or not. As expected of a shoddy slop.
The only point it won is of cost per hour is one aggregation website for rentals, the premium a B300 commands against the $3/hr AMD chip which no provider has in abundance. Never bothered to do TCO of owning the hardware either.