| .. |
|
fa
|
Chores : Typos fixing round 3 (project wide, ggml dir included, comments and user facing msg only) (#2249)
|
2026-08-04 07:15:28 +03:00 |
|
iqk_common.h
|
IQK AVX2: Replace MM256_SET_M128I(x, x) identity broadcasts with _mm256_broadcastsi128_si256 (#2107)
|
2026-07-12 06:55:16 +03:00 |
|
iqk_config.h
|
Use AVX version VNNI intrinsic when AVX512VNNI not available. (#1748)
|
2026-05-09 09:02:06 +03:00 |
|
iqk_cpu_ops.cpp
|
DS4: slowly approaching a meaningful performance (#2165)
|
2026-07-22 17:18:57 +03:00 |
|
iqk_cpu_ops.h
|
model: Ling-3.0 (bailingmoe3) runtime support (#2295)
|
2026-08-13 08:02:50 +02:00 |
|
iqk_flash_attn.cpp
|
DSA: do not copy V rows when V == K (#2287)
|
2026-08-10 18:49:05 +02:00 |
|
iqk_flash_impl.h
|
DS4: slowly approaching a meaningful performance (#2165)
|
2026-07-22 17:18:57 +03:00 |
|
iqk_gemm_1bit.cpp
|
Chores : Typos fixing round 3 (project wide, ggml dir included, comments and user facing msg only) (#2249)
|
2026-08-04 07:15:28 +03:00 |
|
iqk_gemm_1bit.h
|
Faster iq1_s GEMM via repacking to Q8_0_R8 (#517)
|
2025-06-11 15:01:34 +03:00 |
|
iqk_gemm_floats.cpp
|
IQK AVX2: Replace MM256_SET_M128I(x, x) identity broadcasts with _mm256_broadcastsi128_si256 (#2107)
|
2026-07-12 06:55:16 +03:00 |
|
iqk_gemm_floats.h
|
Refactor iqk_mul_mat.cpp (#435)
|
2025-05-22 10:05:51 +03:00 |
|
iqk_gemm_iqk_quants.cpp
|
IQK AVX2: Replace MM256_SET_M128I(x, x) identity broadcasts with _mm256_broadcastsi128_si256 (#2107)
|
2026-07-12 06:55:16 +03:00 |
|
iqk_gemm_iqk_quants.h
|
Much faster CPU prompt processing (part 2) (#533)
|
2025-06-18 07:29:33 +03:00 |
|
iqk_gemm_iquants.cpp
|
Fix IQ3_XXS CPU GEMM (#2224)
|
2026-08-01 08:51:59 +03:00 |
|
iqk_gemm_iquants.h
|
IQ2_XXS: much faster CPU prompt processing (#515)
|
2025-06-11 11:12:30 +03:00 |
|
iqk_gemm_kquants.cpp
|
IQK AVX2: Replace MM256_SET_M128I(x, x) identity broadcasts with _mm256_broadcastsi128_si256 (#2107)
|
2026-07-12 06:55:16 +03:00 |
|
iqk_gemm_kquants.h
|
Faster CPU prompt processing for Q4_K and Q5_K (#525)
|
2025-06-13 07:58:15 +03:00 |
|
iqk_gemm_ktquants.cpp
|
Chores : Typos fixing round 3 (project wide, ggml dir included, comments and user facing msg only) (#2249)
|
2026-08-04 07:15:28 +03:00 |
|
iqk_gemm_ktquants.h
|
Trellis quants: faster CPU prompt processing (#482)
|
2025-06-01 15:24:05 +03:00 |
|
iqk_gemm_legacy_quants.cpp
|
Fix IQ4_NL_R4 GEMM on CPUs with FANCY_SIMD enabled (#2233)
|
2026-08-02 11:15:36 +03:00 |
|
iqk_gemm_legacy_quants.h
|
Much faster CPU prompt processing (part 3) (#534)
|
2025-06-18 15:30:56 +03:00 |
|
iqk_kda.cpp
|
model: Ling-3.0 (bailingmoe3) runtime support (#2295)
|
2026-08-13 08:02:50 +02:00 |
|
iqk_mul_mat.cpp
|
Indexer topk: on the CPU repack Q8_0 indexer cache (#2285)
|
2026-08-10 18:45:43 +02:00 |
|
iqk_mul_mat.h
|
Fused indexer top_k (CPU only) (#2098)
|
2026-07-09 18:04:41 +03:00 |
|
iqk_quantize.cpp
|
Quantization fudge factors (#2361)
|
2026-08-27 17:35:04 +02:00 |
|
iqk_quantize.h
|
MXFP4_R8 (#2196)
|
2026-07-28 08:03:59 +03:00 |
|
iqk_utils.h
|
Fix compilation on clang-cl.exe (#1355)
|
2026-03-04 08:00:28 +01:00 |
7cff686d37