chenchenghao/DeepGEMM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Public release 26/04] Introducing Mega MoE, FP4 Indexer and other features/fixes (#304)

Browse Source 
* Merge with private repo

* Update README

* Update README

* Update README

* Add PyTorch requirements

* Fix sync scopes for MQA logits (#256)

* Update README
This commit is contained in:
Chenggang Zhao
2026-04-17 09:45:14 +08:00
committed by GitHub
parent d30fc36c8f
commit 7f2a703ed5
109 changed files with 12101 additions and 3219 deletions
Download Patch File Download Diff File Expand all files Collapse all files
csrc/utils/hash.hpp
+4 -4
View File
@@ -6,7 +6,7 @@ namespace deep_gemm {
static uint64_t fnv1a(const std::vector<char>& data, const uint64_t& seed) {
uint64_t h = seed;
const uint64_t& prime = 0x100000001b3ull;
const uint64_t prime = 0x100000001b3ull;
for (const char& c: data) {
h ^= static_cast<uint8_t>(c);
h *= prime;
@@ -15,11 +15,11 @@ static uint64_t fnv1a(const std::vector<char>& data, const uint64_t& seed) {
}
static std::string get_hex_digest(const std::vector<char>& data) {
const auto& state_0 = fnv1a(data, 0xc6a4a7935bd1e995ull);
const auto& state_1 = fnv1a(data, 0x9e3779b97f4a7c15ull);
const auto state_0 = fnv1a(data, 0xc6a4a7935bd1e995ull);
const auto state_1 = fnv1a(data, 0x9e3779b97f4a7c15ull);
// Split-mix 64
const auto& split_mix = [](uint64_t z) {
const auto split_mix = [](uint64_t z) {
z = (z ^ (z >> 30)) * 0xbf58476d1ce4e5b9ull;
z = (z ^ (z >> 27)) * 0x94d049bb133111ebull;
return z ^ (z >> 31);