localai-org-maint-bot e5994af49c fix(buun-llama-cpp): match speculative draft split anchor ...

The shared gRPC wrapper stores p_split under the draft sub-structure. Match that exact source spelling so the fork-specific patch stage reaches the build on every architecture.

Assisted-by: Codex:gpt-5 [Codex]

2026-09-12 09:04:07 +00:00

..

patches

fix(buun-llama-cpp): shim cudaMemcpy{To,From}Symbol + WARP_SIZE on fwht128 shuffles

2026-09-12 09:04:07 +00:00

apply-patches.sh

feat(backend): add buun-llama-cpp fork (DFlash + TCQ KV-cache)

2026-09-12 09:04:07 +00:00

Makefile

feat(backend): add buun-llama-cpp fork (DFlash + TCQ KV-cache)

2026-09-12 09:04:07 +00:00

package.sh

feat(backend): add buun-llama-cpp fork (DFlash + TCQ KV-cache)

2026-09-12 09:04:07 +00:00

patch-grpc-server.sh

fix(buun-llama-cpp): match speculative draft split anchor

2026-09-12 09:04:07 +00:00

run.sh

feat(backend): add buun-llama-cpp fork (DFlash + TCQ KV-cache)

2026-09-12 09:04:07 +00:00