public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge 8f8b3b3d0b into 1fe009caed

This commit is contained in:
Kabir Potdar 2026-08-15 20:10:13 +08:00 committed by GitHub
parent 1fe009caed 8f8b3b3d0b
commit 729feb3613
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
ggml/src/ggml-cpu/CMakeLists.txt
View File

@ -302,6 +302,14 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
list(APPEND ARCH_DEFINITIONS __BMI2__ GGML_BMI2)
endif()
else ()
# GCC on 32-bit x86 (i386/i686) defaults to x87 scalar FP (80-bit extended
# precision) even when compiling with -mavx2. Whisper's softmax/logit values
# diverge enough from the SSE2 path that the decoder produces garbage tokens.
# Force SSE FP math to match the precision expected by all SSE/AVX codepaths.
if (CMAKE_SIZEOF_VOID_P EQUAL 4 AND
CMAKE_SYSTEM_PROCESSOR MATCHES "^(i[3-6]86|i686)$")
list(APPEND ARCH_FLAGS -mfpmath=sse -msse2)
endif()
if (GGML_NATIVE)
list(APPEND ARCH_FLAGS -march=native)
else ()

6
ggml/src/ggml-cpu/arch/x86/quants.c
View File

@ -3617,7 +3617,8 @@ void ggml_vec_dot_iq1_s_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const vo
__m256i sumi = _mm256_setzero_si256();
int sumi1 = 0;
for (int ib = 0; ib < QK_K/32; ib += 2) {
#ifdef __BMI2__
// _pdep_u64 is only available on x86_64 (64-bit); use scalar fallback on 32-bit
#if defined(__BMI2__) && defined(__x86_64__)
const uint64_t packed_idx1 = _pdep_u64(*(const uint32_t *)qs, 0x00ff00ff00ff00ffULL) | _pdep_u64(qh[ib], 0x700070007000700ULL);
const uint64_t packed_idx2 = _pdep_u64(*(const uint32_t *)(qs + 4), 0x00ff00ff00ff00ffULL) | _pdep_u64(qh[ib + 1], 0x700070007000700ULL);
const uint16_t *idx1 = (const uint16_t *)(&packed_idx1);
@ -3756,7 +3757,8 @@ void ggml_vec_dot_iq1_m_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const vo
__m256i sumi1 = _mm256_setzero_si256();
__m256i sumi2 = _mm256_setzero_si256();
for (int ib = 0; ib < QK_K/32; ib += 2) {
#ifdef __BMI2__
// _pdep_u64 is only available on x86_64 (64-bit); use scalar fallback on 32-bit
#if defined(__BMI2__) && defined(__x86_64__)
const uint64_t packed_idx1 = _pdep_u64(*(const uint32_t *)qs, 0x00ff00ff00ff00ffULL)
| _pdep_u64(*(const uint16_t*)(qh) & 0x7777, 0xf000f000f000f00ULL);
const uint64_t packed_idx2 = _pdep_u64(*(const uint32_t *)(qs + 4), 0x00ff00ff00ff00ffULL)