Logo
Explore Help
Register Sign In
biondizzle/nvfp4-megamoe-kernel
1
0
Fork 0
You've already forked nvfp4-megamoe-kernel
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
032cb4c7b2edf73843e1cdeb82d7cafdc5834a1c
nvfp4-megamoe-kernel/dsv4/kernels
History
biondizzle c55030a340 P5: clean kernel with runtime branch (single-tile unchanged, multi-tile separate path)
Single-tile path is IDENTICAL to the working pre-P5 kernel.
Multi-tile path uses FA2 online softmax with sOacc accumulator.
Runtime branch on is_multi_tile = (n_kv_tiles > 1).
2026-05-30 08:57:00 +00:00
..
attention
P5: clean kernel with runtime branch (single-tile unchanged, multi-tile separate path)
2026-05-30 08:57:00 +00:00
cache
KV Cache: schema, allocator, pools, manager, append_swa kernel
2026-05-22 00:08:38 +00:00
compressor
Restructure: cutedsl/ -> dsv4/ with proper layering
2026-05-21 17:30:44 +00:00
cuda
Clean up E2M1 dequant: use LUT approach (consultant recommendation)
2026-05-28 16:17:47 +00:00
decode
Restructure: cutedsl/ -> dsv4/ with proper layering
2026-05-21 17:30:44 +00:00
gemm
NVFP4-1.1: Mark fp4_quant.py as toolchain-blocked, clean up test files
2026-05-28 04:59:01 +00:00
indexer
Clean up E2M1 dequant: use LUT approach (consultant recommendation)
2026-05-28 16:17:47 +00:00
router
Router: Blackwell-native fused decode kernel — real CuTeDSL implementation
2026-05-21 22:04:20 +00:00
__init__.py
Restructure: cutedsl/ -> dsv4/ with proper layering
2026-05-21 17:30:44 +00:00
Powered by Gitea Version: 1.25.2 Page: 132ms Template: 13ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API