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
main
vLLM/vllm/models/deepseek_v4/amd
T
History
Taoyu ZhuClaude Opus 5.5vllm-agent
e80b6c642f [ROCm][DSv4] Overlap the unfused shared expert with AITER MegaMoE (#61819)
Signed-off-by: Taoyu Zhu <zhutaoyu97@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
2026-10-18 22:39:38 +08:00
..
__init__.py
[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)
2026-05-18 19:50:02 -07:00
dspark.py
[Bugfix][RL] Load attention sinks through weight_loader for layerwise reload (#57797)
2026-10-14 10:17:58 +00:00
mega_moe.py
[ROCm][DSv4] AITER MegaMoE Fixed-Slot Dispatch For DeepSeek-V4 (#61262)
2026-10-15 19:10:59 +08:00
model.py
[ROCm][DSv4] Overlap the unfused shared expert with AITER MegaMoE (#61819)
2026-10-18 22:39:38 +08:00
mtp.py
[Bugfix][DSv4] Remap Quark MTP layer_quant_config onto draft prefixes (#56054)
2026-10-15 18:51:57 +08:00
rocm.py
[ROCm] gfx1250 optimizations and model enablement (#58800)
2026-10-15 14:51:57 -07:00
Powered by Gitea Version: 1.27.2 Page: 573ms Template: 7ms
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