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
fec64fea75103a1490e7fa0874c55a2292c110b1
vLLM/vllm/models/deepseek_v4
T
History
larryli2-amdandAndreas Karatzas c227aaa3f8 [ROCm] Enable DeepSeek-V4 DSpark speculative decoding on AMD (MI350X / MI355X, gfx950) (#47419)
Signed-off-by: larryli2-amd <larryli2@amd.com>
Signed-off-by: larryli2-amd <Larry.Li@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-10 23:22:19 +08:00
..
amd
[ROCm] Enable DeepSeek-V4 DSpark speculative decoding on AMD (MI350X / MI355X, gfx950) (#47419)
2026-07-10 23:22:19 +08:00
common
[Bugfix] DSV4 TP16 garbage output (#47493)
2026-07-07 21:04:33 -07:00
nvidia
[Bugfix] DSV4 TP16 garbage output (#47493)
2026-07-07 21:04:33 -07:00
xpu
Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)
2026-07-06 14:18:33 +01:00
__init__.py
[ROCm] Enable DeepSeek-V4 DSpark speculative decoding on AMD (MI350X / MI355X, gfx950) (#47419)
2026-07-10 23:22:19 +08:00
attention.py
[Bugfix] DSV4 TP16 garbage output (#47493)
2026-07-07 21:04:33 -07:00
compressor.py
[Bugfix] DSV4 TP16 garbage output (#47493)
2026-07-07 21:04:33 -07:00
quant_config.py
[Bugfix] Fix weight loading issues caused by #41184 (#45054)
2026-06-10 01:20:13 -04:00
sparse_mla.py
[Perf] Cache token_to_req_indices for dsv4, 5x~6x kernel performance improvement (#47474)
2026-07-06 11:17:46 -04:00
Powered by Gitea Version: 1.27.2 Page: 169ms 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