summaryrefslogtreecommitdiff
path: root/ggml/src/ggml.c
AgeCommit message (Expand)Author
2025-06-18New IQ2_KT, IQ3_KT and IQ4_KT, V2 (#529)Kawrakow
2025-06-18Much faster CPU prompt processing (part 2) (#533)Kawrakow
2025-06-17Much faster CPU prompt processing (part 1) (#531)Kawrakow
2025-06-13Faster CPU prompt processing for Q4_K and Q5_K (#525)Kawrakow
2025-06-12iq3_s: much faster GEMM via repacking to q8_0_r8 (#518)Kawrakow
2025-06-11Faster iq1_s GEMM via repacking to Q8_0_R8 (#517)Kawrakow
2025-06-11Much faster iq3_xxs GEMM via repacking to q8_0_r8 (AVX2) (#516)Kawrakow
2025-06-11IQ2_XXS: much faster CPU prompt processing (#515)Kawrakow
2025-06-08Fix non rpc build error (#506)firecoperana
2025-06-08Revert "Rpc improvement (#480)"Iwan Kawrakow
2025-06-08Rpc improvement (#480)firecoperana
2025-06-01Trellis quants: faster CPU prompt processing (#482)Kawrakow
2025-05-29NEON implementation for trellis quants (#471)Kawrakow
2025-05-23Trellis quants with CPU inference (#441)Andrew Chan
2025-05-17IQ5_KS_R4: row-interleaved IQ5_KS (#426)Kawrakow
2025-05-15Adding IQ5_KS - 5.25 bpw quants (#422)Kawrakow
2025-05-13Fix SER (CPU) (#415)Kawrakow
2025-05-10TG improvements for MoE models (#404)Kawrakow
2025-04-29CPU FA improvements (#351)Kawrakow
2025-04-26Fix division by zero bug (#349)Kawrakow
2025-04-26Add support for Cohere2 (#341)Kawrakow
2025-04-25Fix q4_1 and q5_1 on Arm (#348)Kawrakow
2025-04-17Better TG performance for GQA models (CPU) (#332)Kawrakow
2025-03-27Use bf16 instead of fp16 block scales for q8_1 (#292)Kawrakow
2025-03-23Attempt to improve FlashMLA on the CPU (#277)Kawrakow
2025-03-21Convert models to row-interleaved quants using the quantize tool (#272)Kawrakow
2025-03-19Fix ggml_compute_forward_dup_q (#269)Kawrakow
2025-03-18Allow q8_0 cache on the CPU for FlashMLA-2 (#265)Kawrakow
2025-03-13FlashMLA-2 (CPU): faster and smaller compute buffer size (#253)Kawrakow
2025-03-10DeepSeek imatrix stuff (#250)Kawrakow
2025-03-08Faster FlashMLA prompt processing (#246)Kawrakow
2025-03-07Better FlashMLA (#243)Kawrakow
2025-03-03Flash MLA (CPU only) (#240)Kawrakow
2025-03-02SER - Smart Expert Reduction (#239)Kawrakow
2025-03-01A better way to measure the cost of ggml_barrier (#238)Kawrakow
2025-03-01Reduce size of compute buffers (#237)Kawrakow
2025-02-25Give the user the option to override where model weights are stored (#232)Kawrakow
2025-02-23Fused MoE ffn_up and ffn_gate (#229)Kawrakow
2025-02-22Fuse MoE up and gate matrix multiplications (#219)Kawrakow
2025-02-21Hopefully this really fixes the confusion between AVX512 and FANCY_SIMD (#216)Kawrakow
2025-02-19Q8_KV: 8-bit quantization type targeting the KV cache (#208)Kawrakow
2025-02-15Bug fix in activation quantizationIwan Kawrakow
2025-02-15Moving 4D gemm logic from ggml.c to iqk_mul_mat.cpp (#207)Kawrakow
2025-02-11DeepSeek FA support (CPU only) (#200)Kawrakow
2025-02-09Add optional MLA (#188)Kawrakow
2025-02-09Use Q8_K_128 for IQ1_S_R4 and IQ1_M_R4 matrix multiplications (#194)Kawrakow
2025-02-08Revert #79 (#192)Kawrakow
2025-02-06Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)Kawrakow
2025-02-06IQ1_M_R4: better 1.75 bpw quants (#187)Kawrakow
2025-02-05IQ1_S_R4: better 1.5 bpw quants (#185)Kawrakow
generated by cgit v1.2.3 (git 2.25.1) at 2026-01-11 03:47:41 +0000