abcdabcd987

# Results: https://docs.google.com/spreadsheets/d/1t0Txa7Ph9u7Su9LyWpS24vqr9A5FB-FyL0EZNpYOqwg/edit?gid=0#gid=0
# FlashInfer: 28053ac54023fbf3fb552f7be015b0f90a37ed76
# FlashMLA  : accc1695ee0ff996ec63eaf2ebcbf6874ed0e7df
import itertools

import torch
from flash_mla import flash_mla_with_kvcache, get_mla_metadata
from flashinfer import BatchMLAPagedAttentionWrapper
from triton.testing import do_bench  # type: ignore[import]

VictorTaelin

Refactoring Kind's switch with ChatSH

(This is a readable version of my ChatSH session. For the full log, click here.)

Taelin: Hello. We're going to refactor an aspect of the implementation of the Kind language. Are you ready? Start by doing 'ls', then 'cat kind-lang.cabal' to get familiar with the repo.

ChatSH: Certainly! I'm ready to help you refactor an aspect of the Kind language implementation. Let's start by examining the repository structure and the contents of the Cabal file.

ls && echo "---" && cat kind-lang.cabal

VictorTaelin

// Fast block-local prefix-sum on CUDA, using warp-syncs.
// The input is an array of u32. It is mutated in place. Example:
// arr = [1,1,1,1,...]
// Becomes:
// arr = [1,2,3,4,...]
// The number of elements must be equal to threads per block (TPB).

#include <stdio.h>
#include <cuda_runtime.h>

Nicklas373

Encoder av1_nvenc [NVIDIA NVENC av1 encoder]:
    General capabilities: dr1 delay hardware 
    Threading capabilities: none
    Supported hardware devices: cuda cuda d3d11va d3d11va 
    Supported pixel formats: yuv420p nv12 p010le yuv444p p016le yuv444p16le bgr0 bgra rgb0 rgba x2rgb10le x2bgr10le gbrp gbrp16le cuda d3d11
av1_nvenc AVOptions:
  -preset            <int>        E..V....... Set the encoding preset (from 0 to 18) (default p4)
     default         0            E..V....... 
     slow            1            E..V....... hq 2 passes
     medium          2            E..V....... hq 1 pass

moyix

all: gifread gifread.asan gifread.ubsan gifread.coverage

gifread: gifdec.c gifread.c gifdec.h
	$(CC) $(CFLAGS) -o $@ gifdec.c gifread.c $(LDFLAGS)

gifread.asan: gifdec.c gifread.c gifdec.h
	$(CC) $(CFLAGS) -g -fsanitize=address -o $@ gifdec.c gifread.c $(LDFLAGS)

gifread.ubsan: gifdec.c gifread.c gifdec.h
	$(CC) $(CFLAGS) -g -fsanitize=undefined -o $@ gifdec.c gifread.c $(LDFLAGS)

VictorTaelin

// A nano dependent type-checker featuring inductive types via self encodings.
// All computation rules are justified by interaction combinator semantics,
// resulting in major simplifications and improvements over old Kind-Core.
// Specifically, computable annotations (ANNs) and their counterpart (ANN
// binders) and a new self encoding based on equality (rather than dependent
// motives) greatly reduce code size. A more complete file, including
// superpositions (for optimal unification) is available on the
// Interaction-Type-Theory repository.
// Credits also to Franchu and T6 for insights.

ibireme

// =============================================================================
// XNU kperf/kpc demo
// Available for 64-bit Intel/Apple Silicon, macOS/iOS, with root privileges
//
//
// Demo 1 (profile a function in current thread):
// 1. Open directory '/usr/share/kpep/', find your CPU PMC database.
//    M1 (Pro/Max/Ultra): /usr/share/kpep/a14.plist
//    M2 (Pro/Max):       /usr/share/kpep/a15.plist
//    M3:                 /usr/share/kpep/as1.plist

Matthias247

A case for CancellationTokens

Background

The Rust async working group is currently actively discusing on ways to improve async/await. Niko Matsakis documented the main goals and ideas in the async vision document.

As part of the improved async ecosytem, users should be able to make use of

haxscramper

Base C++ class cppbase.cpp

#pragma once

#include <stdio.h>

struct CppBase {
  virtual void baseMethod(int arg) {
    printf("arg from nim - %d -\n", arg);

kobigurk

pragma solidity ^0.5.15;

contract BLS {
    // Field order
    uint256 constant N = 21888242871839275222246405745257275088696311157297823662689037894645226208583;

    // Negated genarator of G2
    uint256 constant nG2x1 = 11559732032986387107991004021392285783925812861821192530917403151452391805634;
    uint256 constant nG2x0 = 10857046999023057135944570762232829481370756359578518086990519993285655852781;
    uint256 constant nG2y1 = 17805874995975841540914202342111839520379459829704422454583296818431106115052;