happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml/src/ggml-cpu
History
muggle-stack 342c728d03
ggml : fix SpaceMit IME array out-of-bounds in task assignment (#16629) 
Fix incorrect task-to-batch index calculation in the quantization phase.

The bug caused out-of-bounds access to qnbitgemm_args array when
compute_idx exceeded per_gemm_block_count_m, leading to invalid
pointer dereferences and SIGBUS errors.

Correctly map tasks to batches by dividing compute_idx by
per_gemm_block_count_m instead of block_size_m.

Example:
  batch_feature=1, gemm_m=30, block_size_m=4
  per_gemm_block_count_m = 8, task_count = 8

  Old: gemm_idx = 4/4 = 1 (out of bounds  New: gemm_idx = 4/8 = 0 (correct)

Tested on SpaceMit K1 RISC-V64 with qwen2.5:0.5b model.

Co-authored-by: muggle <mingjun.rong@spacemit.com>
 		2025-10-17 13:01:23 +03:00
..
amx ggml : fix unaligned access in AMX code (#16315) 2025-10-06 16:05:27 +03:00
arch devops: add s390x & ppc64le CI (#15925) 2025-09-27 02:03:33 +08:00
cmake ggml : build backends as libraries (#10256) 2024-11-14 18:04:35 +01:00
kleidiai kleidiai: kernel interface refactoring (#16460) 2025-10-09 10:29:17 +03:00
llamafile llamafile: PowerPC Sgemm Optimization (#15558) 2025-08-26 23:35:25 +08:00
spacemit ggml : fix SpaceMit IME array out-of-bounds in task assignment (#16629) 2025-10-17 13:01:23 +03:00
CMakeLists.txt kleidiai : fix work size and threads sync for fp16 (#16246) 2025-09-30 10:07:20 +03:00
arch-fallback.h ggml-cpu: implement MXFP4 SIMD for s390x (#16193) 2025-09-26 13:27:25 +03:00
binary-ops.cpp cpu: de-duplicate some of the operators and refactor (ggml/1144) 2025-03-30 08:33:31 +03:00
binary-ops.h cpu: de-duplicate some of the operators and refactor (ggml/1144) 2025-03-30 08:33:31 +03:00
common.h ggml : refactor forward_dup for cpu backend (#16062) 2025-09-19 06:31:56 +02:00
ggml-cpu-impl.h ggml : fix build broken with -march=armv9-a on MacOS (#16520) 2025-10-13 15:48:47 +03:00
ggml-cpu.c ggml-cpu: replace putenv with setenv for const-correctness (#16573) 2025-10-16 08:10:32 +03:00
ggml-cpu.cpp ggml: riscv: add riscv spacemit backend (#15288) 2025-09-29 17:50:44 +03:00
hbm.cpp ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00
hbm.h ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00
ops.cpp cpu : add FLOOR, CEIL, ROUND and TRUNC unary operators (#16083) 2025-10-15 21:24:51 +02:00
ops.h ggml: add ops for WAN video model (cuda && cpu) (#15669) 2025-09-04 10:38:49 +02:00
quants.c llama : add gpt-oss (#15091) 2025-08-05 22:10:36 +03:00
quants.h llama : add gpt-oss (#15091) 2025-08-05 22:10:36 +03:00
repack.cpp ggml : repack block_iq4_nlx8 (#14904) 2025-08-13 11:09:39 +03:00
repack.h ggml : repack block_iq4_nlx8 (#14904) 2025-08-13 11:09:39 +03:00
simd-mappings.h ggml : fix loongarch lsx compilation error (#15864) 2025-09-25 12:22:55 +03:00
traits.cpp ggml : fix fallback to CPU for ununsupported ops (#15118) 2025-08-06 14:37:35 +02:00
traits.h ggml : fix fallback to CPU for ununsupported ops (#15118) 2025-08-06 14:37:35 +02:00
unary-ops.cpp cpu : add FLOOR, CEIL, ROUND and TRUNC unary operators (#16083) 2025-10-15 21:24:51 +02:00
unary-ops.h cpu : add FLOOR, CEIL, ROUND and TRUNC unary operators (#16083) 2025-10-15 21:24:51 +02:00
vec.cpp ggml : fix scalar path for computing norm (#16558) 2025-10-13 11:22:27 +03:00
vec.h ggml : Fix FP16 ELU positive branch (#16519) 2025-10-12 08:25:37 +03:00