Kawrakow 9c1c74acda Step-3.5-Flash support (#1231) ... * WIP * This works but is slow * Turn off the up / gate clamps for now * OK we need the clamping * Fuse the clamp (CUDA) * Fuse the clamp (CPU) * WIP * Be able to use merged q, k, v * Be able to use merged up/gate experts * Fuse the clamp (CUDA mmvq)		2026-02-05 08:13:22 +02:00
..
fa	Better CPU FA thread strategy	2026-01-31 15:46:16 +00:00
iqk_common.h	Unroll for loop for repacked BF16 MATMUL (#1047)	2025-12-08 06:09:45 +01:00
iqk_config.h	Fix termux/android build (#336)	2025-04-21 09:13:46 +02:00
iqk_cpu_ops.cpp	Faster adaptive_p sampling (#1165)	2026-01-19 16:03:09 +02:00
iqk_cpu_ops.h	Faster adaptive_p sampling (#1165)	2026-01-19 16:03:09 +02:00
iqk_flash_attn.cpp	Fix CPU FA work buffer size (#1216)	2026-02-02 12:39:41 +02:00
iqk_flash_impl.h	Enable CUDA graphs for MoE models + GPT-OSS support (#689)	2025-08-15 09:18:07 +03:00
iqk_gemm_1bit.cpp	AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710)	2025-08-22 06:27:07 +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	Unroll for loop for repacked BF16 MATMUL (#1047)	2025-12-08 06:09:45 +01:00
iqk_gemm_floats.h	Refactor iqk_mul_mat.cpp (#435)	2025-05-22 10:05:51 +03:00
iqk_gemm_iqk_quants.cpp	AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710)	2025-08-22 06:27:07 +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	AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710)	2025-08-22 06:27:07 +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	AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710)	2025-08-22 06:27:07 +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	Adding IQ1_KT - 1.75 bpw SOTA quants (#616)	2025-07-20 10:05:23 +02:00
iqk_gemm_ktquants.h	Trellis quants: faster CPU prompt processing (#482)	2025-06-01 15:24:05 +03:00
iqk_gemm_legacy_quants.cpp	Add missing AVX512 operators for MSVC (#948)	2025-11-14 06:58:51 +02:00
iqk_gemm_legacy_quants.h	Much faster CPU prompt processing (part 3) (#534)	2025-06-18 15:30:56 +03:00
iqk_mul_mat.cpp	Step-3.5-Flash support (#1231)	2026-02-05 08:13:22 +02:00
iqk_mul_mat.h	Step-3.5-Flash support (#1231)	2026-02-05 08:13:22 +02:00
iqk_quantize.cpp	Hadamard transforms for K-cache - CPU only (#1033)	2025-12-04 06:51:11 +01:00
iqk_quantize.h	Check for NaNs while loading the model. (#727)	2025-08-27 19:00:17 +03:00
iqk_utils.h	Add missing AVX512 operators for MSVC (#948)	2025-11-14 06:58:51 +02:00