Ettore Di Giacinto 9787bee48b fix(buun-llama-cpp): shim cudaMemcpy{To,From}Symbol + WARP_SIZE on fwht128 shuffles ...

Two more hipblas-only build failures in buun's fattn.cu, fixed under the
same patches/ infrastructure:

1. cudaMemcpyToSymbol / cudaMemcpyFromSymbol — buun's Q² calibration +
   TCQ codebook upload paths call the symbol variants of cudaMemcpy.
   ggml/src/ggml-cuda/vendors/hip.h aliases every other cudaMemcpy*
   name (cudaMemcpy, cudaMemcpyAsync, cudaMemcpy2DAsync, …) but the
   symbol pair was never added. 15+ "use of undeclared identifier"
   errors across fattn.cu lines 40, 54, 74-76, 94, 100-101, 371, 883,
   905, 954, 976, 1449, 1463. Add the two missing aliases alongside
   the existing memcpy block.

2. __shfl_xor_sync fwht128 calls — same 3-arg omission pattern as the
   earlier argmax top-K fix. Lines 512 (ggml_cuda_fwht128 intra-warp
   butterfly) and 536 (fwht128_store_half neighbor fetch) drop the
   width argument that hip.h:33 requires. Add WARP_SIZE.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-04-24 20:09:36 +00:00

..

patches

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

2026-04-24 20:09:36 +00:00

apply-patches.sh

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

2026-04-24 12:52:53 +00:00

Makefile

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

2026-04-24 12:52:53 +00:00

package.sh

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

2026-04-24 12:52:53 +00:00

patch-grpc-server.sh

fix(buun-llama-cpp): drop logit_bias_eog arg from params_from_json_cmpl

2026-04-24 12:52:53 +00:00

run.sh

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

2026-04-24 12:52:53 +00:00