mudler-agentandEttore Di Giacinto 81eaca8768 fix(turboquant): extend D512 flash-attn patch to all turbo V types (#12234) ...

The previous patch only removed DECL_FATTN_VEC_CASE_D512 for turbo2_0
and turbo3_0 V cache types. turbo4_0 also overflows shared memory
(0x10100 bytes > 0xc000 max), causing ptxas errors on CUDA 12/13.

Additionally, the previous patch was incomplete: it only removed the
template instantiations but not the dispatch calls in fattn.cu or the
extern declarations in fattn-vec.cuh. This caused linker errors
(undefined reference to ggml_cuda_flash_attn_ext_vec_case_d512).

This patch removes all three layers for all turbo V types:
- Template instance .cu files (DECL_FATTN_VEC_CASE_D512)
- Dispatch calls in fattn.cu (FATTN_VEC_CASE_D512)
- Extern declarations in fattn-vec.cuh (extern DECL_FATTN_VEC_CASE_D512)

Signed-off-by: mudler <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

2026-09-24 08:01:28 +02:00

..

0001-hip-guard-copy2d-peer-fastpath.patch

fix(turboquant): supersede stale dependency bump (#11064)

2026-07-23 10:48:24 +02:00

0002-remove-d512-turbo-shared-mem-overflow.patch

fix(turboquant): extend D512 flash-attn patch to all turbo V types (#12234)

2026-09-24 08:01:28 +02:00