Logo
Explore Help
Sign In
iHore/vLLM
Watch 8
Star 0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
65ce85fcdcd79770eeb8cd5eeb4e4ba06120bf6d
vLLM/vllm/models/deepseek_v4/common/ops
T
History
Andreas Karatzas 6b68db441e [ROCm] Fix DeepSeek V4 indexer numerics and coverage (#50803)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-08-20 09:34:00 +00:00
..
__init__.py
[New model] Kimi K3 (#50000)
2026-07-30 03:49:58 -07:00
cache_utils.py
Revert DSv4 eager workspace reuse (#52836)
2026-08-18 17:02:59 -07:00
fused_compress_quant_cache.py
[ROCm][DSV4][Perf] Optimize Triton sparse-MLA decode on gfx950 (#52212)
2026-08-16 12:16:46 -07:00
fused_indexer_q.py
[ROCm] Fix DeepSeek V4 indexer numerics and coverage (#50803)
2026-08-20 09:34:00 +00:00
fused_inv_rope_fp8_quant.py
[XPU] FP8 o_proj with fp8_bmm and load-time scale transpose (#48334)
2026-07-20 16:32:03 +08:00
fused_mtp_input_rmsnorm.py
[Model Refactoring] Remove torch compile dependency in DSv4 (#43746)
2026-05-28 14:26:25 +00:00
save_partial_states.py
[DSv4] Refactor compressor & Fix ROCm compatibility (#43710)
2026-05-26 19:56:46 -07:00
Powered by Gitea Version: 1.27.2 Page: 324ms Template: 10ms
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