Skip to content

model : deepseek41 quantized K cache, shared prompt tokens, Engram host placement - #293

Open
danielhanchen wants to merge 5 commits into
dsv41-cuda-exactfrom
dsv41-runtime
Open

model : deepseek41 quantized K cache, shared prompt tokens, Engram host placement#293
danielhanchen wants to merge 5 commits into
dsv41-cuda-exactfrom
dsv41-runtime

Merge #289 test fixes (quantized KV context error, add_kv int32 insta…

89d61f9
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs