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
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
..
cache
Flush compressor: schema fix, prepare_forward, flush_write kernels, state rotation
2026-05-22 00:25:47 +00:00
kernels
P5: clean kernel with runtime branch (single-tile unchanged, multi-tile separate path)
2026-05-30 08:57:00 +00:00
layers
NVFP4-1.1 integration: GPU-only quantize kernel + MoE pipeline wiring
2026-05-25 16:19:07 +00:00
loader
Restructure: cutedsl/ -> dsv4/ with proper layering
2026-05-21 17:30:44 +00:00
model
Fix layer construction: match existing API signatures, add RMSNorm impl
2026-05-21 23:31:58 +00:00
ops
Stage E: head-packed MQA/GQA, batch dim, custom_op, integration API
2026-05-27 15:15:03 +00:00
reference
Restructure: cutedsl/ -> dsv4/ with proper layering
2026-05-21 17:30:44 +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: 113ms Template: 8ms
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