-
Notifications
You must be signed in to change notification settings - Fork 185
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
DeepSeek-V4.1 leaves 15% on the table: the i8mm trunk kernel is built, measured and off by default
enhancementNew feature or requestNew feature or requestStatus: Open.#70 In sqliteai/warp;A Qwen load sets the trunk kernel for the whole process, so a Kimi context already open switches to i8mm
bugSomething isn't workingSomething isn't workingStatus: Open.#68 In sqliteai/warp;- Status: Open.#67 In sqliteai/warp;
- Status: Open.#65 In sqliteai/warp;
- Status: Open.#58 In sqliteai/warp;
- Status: Open.#49 In sqliteai/warp;
Gate 7: Strix Halo (128 GB, Zen 5 AVX-512/VBMI) dataset for the fine cache sweep
help wantedExtra attention is neededExtra attention is neededStatus: Open.#37 In sqliteai/warp;- Status: Open.#24 In sqliteai/warp;
CUDA backend: what would have to be true for it to pay
enhancementNew feature or requestNew feature or requesthelp wantedExtra attention is neededExtra attention is neededStatus: Open.#11 In sqliteai/warp;