Logo
Explore Help
Sign In
iHore/vLLM
Watch 8
Star 0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
sm86
vLLM/vllm/models/qwen4_exp/nvidia/ops
T
History
trienebutdienekimseunghyunClaude Opus 5.5Thien Tran
77154ca611 [Perf][Model][Qwen4Exp] QSA: decode four FP8 e4m3 bytes per register below sm_89 (#60992)
Signed-off-by: kimseunghyun <hellonypcteam@gmail.com>
Co-authored-by: kimseunghyun <hellonypcteam@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
2026-10-14 13:06:16 +08:00
..
cute_dsl
[Perf][Qwen4Exp] Fuse HC down projection and SiLU on NVIDIA (#58957)
2026-09-28 18:51:38 +08:00
__init__.py
[Model] Support Qwen3.8-Flash-Next (#53896)
2026-08-31 05:57:56 +00:00
hc.py
[Kernel] Reuse Qwen4Exp HC combine-norm for MTP input (#54687)
2026-09-04 02:57:56 -07:00
qsa_indexer.py
[Qwen3.8-Flash-Next] Avoid memory fragmentation in QSA indexer logits workspace (#57105)
2026-09-27 10:11:52 +08:00
qsa_prepare.py
[Perf][Qwen4Exp] Merge QSA QKVG and indexer QK projections (#59533)
2026-10-05 07:03:29 +00:00
qsa.py
[Perf][Model][Qwen4Exp] QSA: decode four FP8 e4m3 bytes per register below sm_89 (#60992)
2026-10-14 13:06:16 +08:00
Powered by Gitea Version: 1.27.2 Page: 759ms Template: 8ms
Auto
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