Daniel Stokes

@kmurray This changes Odin II's BLIF output slightly which seems to have had some QoR changes for VPR. The issues on Travis appear to be improvements. What do I need...

Running the regression tests (with -create_golden to regenerate golden) for basic, strong and nightly I get this error: ``` vtr_func_formal: k6_frac_N10_40nm.xml/stereovision3.v/common file : abc.lec.out failed: Couldn't determine Logical Equivalence status...

@vnkc1 can you try the solution of switching device map from auto to cpu as suggested here https://github.com/NVIDIA/TensorRT-LLM/issues/1440

I'm not sure I understand how that prevents you loading on the CPU? If you are quantizing to FP8 (Hopper only) you should be using quantize.py. If you are quantizing...

Sure thing I opened PR #120

>For the record the code above above produces 16bits/4 zeros (not 12bits, 3 zeros) at the end because the 48bit engine (ranlux48). Even if the bug wasn't there the 4th...

I am happy to implement this myself, but I would appreciate some design guidance on what the most suitable API would be. I couldn't find anything already in thrust with...

Hi @miscco, Actually this function does have a constant cost, each element is entirely independent and can be computed in any order. The RNG is only invoked once on construction...

I haven't done the formal analysis, in the worst case one call to `iterate_until_in_range` can take O(n) time. However, for each iteration it can be roughly modelled as a (worst...

To elaborate on how this works, feistel_bijection works on a power of two. To generalize this to a non power of two, we round up to a power of two...