summaryrefslogtreecommitdiff
path: root/ggml/src
AgeCommit message (Collapse)Author
2025-04-30Fix IQK_FA_ALL_QUANTS on AVX2 (#360)Kawrakow
* Fix IQK_FA_ALL_QUANTS on AVX2 * Make it also work, not just compile --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-29CPU FA improvements (#351)Kawrakow
* FA: provide work buffer for K repacking * Add header to avoid comp0iler warnings * WIP * WIP * WIP * WIP * Slightly better * WIP (Zen4) * WIP * Try to improve for unusual number of heads/number of threads * Use mul_mat_qX_0_q8_2_Tx for q6_0 in FA * Use mul_mat_qX_0_q8_2_Tx for q4_0 in FA * Use Sum4q4 for q4_0 * WIP * WIP * Much better FA TG with q8_0 KV cache Just repack it even for TG. But do the repacking for k_step rows, not the whole K tensor. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-26Fix division by zero bug (#349)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-26Add support for Cohere2 (#341)Kawrakow
* Add support for Cohere2 * Fixe IQ4_NL on AVX2 * Command-A needs fp32 precision for K*Q --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-25Fix q4_1 and q5_1 on Arm (#348)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-25Add ability to manually set arch flags (#347)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-25Fix FA on ARM (#346)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-24cuda: use switch in constexpr funcs (#343)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-21Fix termux/android build (#336)saood06
* Attempt fix * Attempt fix 2 * Attempt fix 3 * Attempt fix 4 * Attempt fix 5 * Attempt fix 6 * Attempt fix 7 * Attempt fix 8 * Attempt fix 9 * Attempt fix 10 * Attempt fix 11 * Attempt fix 12 * Attempt fix 13
2025-04-17Better TG performance for GQA models (CPU) (#332)Kawrakow
* Slightly better CPU TG performance for GQA * Better CPU FA implementation for TG when GQA * Minor --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-15Better gemm/gemv on AVX2 fr q4_0_r8 (#331)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-15Allow q8_0 KV cache for head size 256 (#330)Kawrakow
* Allow q8_0 KV cache for head size 256 * We need also these --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-13Improved IQ1_M quantization (#327)Kawrakow
* Much faster and it looks like better iq1_m quantiation * Cleanup * Minor --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-07Better iq2_xs quantization (#312)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-07Add copyright notices (#317)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-05We need to synchronize before using device to host async memcpy (#313)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-04Add -flax-vector-conversions for GCC on ARM (#311)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-03Metal: FA and FlashMLA (#310)Kawrakow
* Metal: WIP to update Metal FA implementation Dk=192, Dv=128 works, but not Dk = 576, Dv = 512 * Metal FA: go to float * WIP * Metal FA: MLA options now all work --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-03Fix GCC compilation errors on ARM (#309)Kawrakow
* Fix GCC compilation errors on ARM * One more --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-03Metal: much faster MoE prompt processing (#307)Kawrakow
* MoE improvements on Metal This version beats mainline, there are things I don't understand: * Mianline has effectively gone to GEMV for MUL_MAT_ID. We can do the same, but we are 30% slower. Why? * Using actual GEMM, we beat mainline with ubtach size of 128. But then performance degrades. Why? * Some cleanup * Much better --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-01Fix ARM_NEON build failure due to q8_2 (#303)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-01Quantization improvements (2) (#302)Kawrakow
* iq3_k: slightly better quantization Not much of a difference for most models, but this change avoids what it looks like a catastrophic failure for DeepSeek-Lite (PPL is now 7.041 vs 7.314 on main). * Small improvement for type-1 quants --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-01Fix #300 (#301)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-29Quantization improvements (#295)Kawrakow
* Better make_qx_quants Tested with q4_0 and q3_K (pure, imatrix), and the improvement is quite significant. * Sae for iq4_nl, iq4_xs --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-27Use bf16 instead of fp16 block scales for q8_1 (#292)Kawrakow
* WIP - not working * q8_0 without bells and wistles works * It works for q8_0 * Use bf16 instead of f16,int16 * q4_0_r8 * q5_0_r4 * q6_0_r4 * Also q4_1 and q5_1 * q8_0_r8 on avx2 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-25CUDA: better MoE implementation (#283)Kawrakow
* Make fused MoE reproducible As a bonus, peak performance at pp2048 with u_batch = 2048 is ~8% better. * Slightly better * Also do it for non-fused mul_mat_id --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-23Improve DeepSeek batched processing speed (#282)Kawrakow
* Improve DeepSeek batched processing speed * Revert the commented out section in iqk_mul_mat.cpp It does have some benefit at long contexts. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-23Attempt to improve FlashMLA on the CPU (#277)Kawrakow
* Fix it for nth > rk2 * Handle rk2%nth_k != 0 * Cleanup --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-22Native build ooption for CUDA when GGML_NATIVE is set (#280)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-22Fighting with cmake (#279)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-21Convert models to row-interleaved quants using the quantize tool (#272)Kawrakow
* Repack a model with the quantize tool * WIP * Fixed various issues As we don't have a way to tell if a repacked quant has been modified, I had to remove the modification at the expense of a slight decrease in performance. This affects q8_0_r8, q8_KV_r8, q8_k_r8 on Zen4, and q4_0_r8 on ARM. * Create wk_b and wv_b as Q8_0_R8 if the wkv_b type is interleaved * Fix GCC 13.3 compilation error * Another one * Add missing include --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-19Fix ggml_compute_forward_dup_q (#269)Kawrakow
I broke it with PR #265. I was testing with a model where the wk_b and wk_v tensors were present, so didn't need to be computed, so didn't notice that the change I made to ggml_compute_forward_dup_q breaks that computation. Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-19Prevent FlashMLA-1 from running on CUDA (#268)Kawrakow
as it is not supported. Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-18Allow q8_0 cache on the CPU for FlashMLA-2 (#265)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-18Make Q8_0 KV cache work with mla=2,fa on CUDA (#264)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-18Fix #261 (#262)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-18Compile time option to use bf16 for qunts without MMQ kernels (#261)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-18FlashMLA-2: reduce compute buffer size (CUDA and CPU) (#260)Kawrakow
* FlashMLA-2: eliminate intermediate f32 tensors This works on the CPU. PP performance is ~13% better for 16k tokens and compute buffer is quite a bit smaller. * FlashMLA-2: enable fast path only on the CPU for now I did implement the necessary ops on CUDA, but something is still wrong there, so for now we only use it when running CPU-only. * FlashMLA-2: slightly smaller computer buffer size * Prepare wk_b when loading DeepSeek models (if wk_b is missing) * Add some comments * Fix case where wkv_b is quantized with k- or i-quants. * Fix CUDA There is an issue with quantized GEMV on CUDA when the left operand (the matrix) is not contiguous. So, for now, we also create wv_b during model loading and use that instead of the 3D view of wkv_b. * FlashMLA-2: avoid conversions to f32 also on CUDA * Be able to compute for more than 65535 tokens On CUDA just a quick hack that allows us to cancatenate tensors with more than 65535 rows along zroth dimension as needed by FlashMLA-2. Also needed some care in the perplexity tool to avoid int overflows when evaluating the computed logits. * Reduce memory usage for FlashMLA-2 Oh, also fix int overflow in the CUDA concat implementation. It is funny how the llama.cpp 64-bit police has gone (almost) everywhere and replaced 32-bit ints with 64-bit ints, needed or not, but hasn't done it where it is actually needed. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-13FlashMLA-2 (CPU): faster and smaller compute buffer size (#253)Kawrakow
* FlashMLA-2: eliminate intermediate f32 tensors This works on the CPU. PP performance is ~13% better for 16k tokens and compute buffer is quite a bit smaller. * FlashMLA-2: enable fast path only on the CPU for now I did implement the necessary ops on CUDA, but something is still wrong there, so for now we only use it when running CPU-only. * FlashMLA-2: slightly smaller computer buffer size --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-12MLA-2: Allow usage of q8_0 for KV cache on CUDA (#252)Kawrakow
* FlashMLA(CUDA): WIP to allow q8_0 quantized cache * WIP * FlashMLA(CUDA) - allow q8_0 for KV cache This works, and PP is not bad, but TG is still quite a bit slower. * FlashMLA(CUDA) - allow q8_0 for KV cache This is better. ~9% slower than f16 cache for short contexts, nearly on par at 16k tokens. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-10DeepSeek imatrix stuff (#250)Kawrakow
* This gives us ~20% TG speedup for DeepSeek on CUDA * Slightly better * Also do it for plain (not fused) mul_mat_id * Guard against numerical precision issues for MLA on CUDA * imatrix: wv_b <-> wkv_b --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-10Faster MoE token generation on CUDA (#248)Kawrakow
* This gives us ~20% TG speedup for DeepSeek on CUDA * Slightly better * Also do it for plain (not fused) mul_mat_id * Guard against numerical precision issues for MLA on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-08Faster FlashMLA prompt processing (#246)Kawrakow
* FlashMLA-2: faster prompt processing The current MLA implementation computes wv_b * (k_cache * softmax(k_cache * (wk_b*q))) This leads to 3.4X more multiply-adds (madds) compared to standard attention. Due to the resulting tensor shapes, TG is still faster than standard attention because the k_cache*(wk_b*q) and k_cache*(softmax(k_cache * (wk_b*q))) multiplications become GEMMs, so the additional madds are more than compensated for due to the much higher performance of GEMMs compared to GEMVs. But for PP, where we are dealing with GEMMs in both cases, the additional madds needed for MLA lead to lower performance, with the performance gap increasing with context length. So, then, when we are dealing with PP, we can rearrange the above to (wv_b * k_cache) * softmax( (wk_b^T*k_cache) * q), thus transforming it into the standard attention mechanism. We do need two additional matrix multiplications (which in practice is done as a single wkv_b * k_cache GEMM) with the *entire* K cache. But this is still cheaper than MLA, as we end up with 1.8X the madds required by standard attention. Oh, these figures are for the DeepSeek-V3/R1/Lite attention architecture. This leads to a significant PP performance increase compared to standard MLA with FA. There are many upsides to this: * If we only apply the above trick when we are processing more than X tokens (with suitable chosen X), TG performance stays the same as MLA with FA * We still need to store just the K-cache, so 576 entries per layer for DeepSeek-V3/R1/Lite * We get significantly better PP performance * We can use MLA+FA on CUDA. It works already with this commit for PP, something is not yet quite right for TG. The downside is that it only works with fp16 cache (for now). This is so because we need to convert the cache to fp32, else we cannot do the wkv_b * k_cache matrix multiplication (which in ggml requires the second operand to be fp32). But converting (copying) to fp32 only works for f16, bf16 and f32 tensors, so no luck with quantized cache. Another reason that we need to convert to fp32 is that the cache contains the RoPE'd portion, which we need to concatenate to the result of the wkv_b * k_cache matrix multiplication. Also this op works only when the tensors being concatenated are both fp32. So much about ggml being a general purpose ML library. * FlashMLA-2: on the CPU it now works for quantized cache except for q8_KV (q8_KV has row meta data, and there is still some confusion with row sizes because of that). * FlashMLA-2: on the CPU it now works also with q8_KV --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-07Better FlashMLA (#243)Kawrakow
* This is a better FA for TG It should benefit MLA and GQA. Tested to work with DeepSeek-Lite MLA, not yet for GQA. For tg64@pp8192 it is ~13% faster than MLA without FA, and 57% faster that the main branch FA. * WIP * Cleanup --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-05DeepSeek CUDA Flash Attention (#241)Kawrakow
* WIP CUDA FA with Dk != Dv * WIP * CUDA FA WIP - It actually works! No TG yet, but for PP I can run FA with fp16 cache and it gets the same answer. * CUDA FA WIP - it now works for Q8_0 + Q8_0 for KV cache * CUDA FA WIP - TG, not working yet. * CUDA FA with Dk != Dv: it works now for DeepSeek --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-03Flash MLA (CPU only) (#240)Kawrakow
* FlashMLA - it finally works (on the CPU) * FlashMLA: allow for f16 and bf16 cache in addition to q8_0 * It works with ggml FA, not with iqk FA * WIP * FlashMLA: it now works with iqk I had forgotten to divide the Q stride by sizeof(float) and that's why, very cobfusingly, it was working for TG but not for PP. * WIP * FlashMLA: that should be it for now --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-02SER - Smart Expert Reduction (#239)Kawrakow
* A better way to measure the cost of ggml_barrier * Smart expert selection * Add ser option to llama-bench --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-01A better way to measure the cost of ggml_barrier (#238)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-01Reduce size of compute buffers (#237)Kawrakow
* This reduces compute buffer size for MLA * This should accomplish it for standard attention * Much better * Better concat for contiguous tensors If all the op does is to concatenate the second tensor to the first, why would we want to have a loop? --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-02-27Option to use MLA without a transposed cache (#235)Kawrakow
The `-mla` command line option turns into an int from a bool. mla = 0: use standard attention mla = 1: use MLA with transposed cache mla > 1: use MLA without transposed cache Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-19 15:29:36 +0000