summaryrefslogtreecommitdiff
path: root/examples/quantize
AgeCommit message (Collapse)Author
2025-02-06Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)Kawrakow
* Rename q4_0_r4 to q4_0_r8 to reflect actual row interleaving * Rename q8_0_r4 to q8_0_r8 to reflect actual row interleaving * Rename iq4_xs_r4 to iq4_xs_r8 to reflect actual row interleaving --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-02-06IQ1_M_R4: better 1.75 bpw quants (#187)Kawrakow
* iq1_m_r4: basics (quantize/dequantize) * iq1_m_r4: Zen4 gemm * iq1_m_r4: neon gemm * iq1_m_r4: switch to q8_0_x4 also on AVX2/Zen4 With the deltas being per group of 8, we cannot make use of the q8 sums stored in q8_1, so we get a tiny gain by using q8_0_x4. * iq1_m_r4: rename mul_mat_iq1_m_r4_q8_1 to mul_mat_iq1_m_r4_q8_0 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-02-05IQ1_S_R4: better 1.5 bpw quants (#185)Kawrakow
* iq1_s_r4: basics - quantize/dequantize * iq1_s_r4: gemm/gemv works on AVX2/Zen4 * Don't forget to make sure we have a multiple of 4 rows per thread * iq1_s_r4: this is better * iq1_s_r4: fix Zen4 after AVX2 changes * iq1_s_r4: NEON gemm/gemv * iq1_s_r4: more bits for shared experts With this mix we arrive at PPL(512) = 9.4140 for Deepseek-Lite using 1.766 bpw for the repeating layers. On the Ryzen-7950X we get PP-512 = 494 t/s and TG-128 = 52 t/s @ 16 threads. * Forgotten counter increment * iq1_s_r4: slightly faster AVX2/Zen4 gemm/gemv * Compiler warnings --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-23IQ3_S_R4 (#162)Kawrakow
* iq3_s_r4: WIP * iq3_s_r4: Zen4 * iq3_s_r4: slightly better Zen4 * iq3_s_r4: AVX2 * iq3_s_r4: NEON * iq3_s_r4: rearrange quants * iq3_s_r4: rearranged quants - AVX2 * iq3_s_r4: rearranged quants - NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-21IQ2_S_R4 (#156)Kawrakow
* iq2_s_r4: Zen4 * Minor * iq2_s_r4: NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-21IQ2_XS_R4 (#155)Kawrakow
* iq2_xs_r4: Zen4 * iq2_xs_r4: AVX2 * iq2_xs_r4: slightly better matrix x vector on AVX2 * iq2_xs_r4: NEON - not much better than iq2_xs * iq2_xs_r4: slightly better NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-20IQ2_XXS_R4 (#154)Kawrakow
* iq2_xxs_r4: Zen4 Disapointing gain: 134.7 t/s -> 151.1 t/s for PP-512 TG-128 is better: 3.45 -> 4.61 t/s @ 1 thread * Minor * iq2_xxs_r4: NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-20IQ3_XXS_R4 (#153)Kawrakow
* iq3_xxs_r4: 1st shot on Zen4 PP-512: 107 t/s -> 137 t/s TG-128(1 thread): 2.64 t/s -> 3.44 t/s * iq4_xxs_r4: WIP * iq4_xxs_r4: 1st shot at AVX2 Note: there is a bug in the AVX2 implementation for nrc_y = 1 for IQ quants with blocks of 32. I have fixed it for now by using the nrc_y > 1 implementation (which works) also for nrc_y = 1. * iq3_xxs_r4: NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-18IQ4_KS_R4 (#150)Kawrakow
* iq4_ks_r4: Zen4 * iq4_ks_r4: AVX2 * iq4_ks_r4: WIP * iq4_ks_r4: slightly better Zen4 * iq4_ks_r4: slightly better Zen4 * iq4_ks_r4: NEON * Minor --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-18IQ5_K_R4 (#149)Kawrakow
* iq5_k_r4: Zen4 Much slower than the others. * iq5_k_r5: WIP * Minor * iq5_k_r4: fix AVX2 nrc_y = 1 case * iq5_k_r4: better Zen4 But TG is still slower than iq5_k * iq5_k_r4: slightly better AVX2 * iq5_k_r4: NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-17IQ2_K_R4 (#146)Kawrakow
* iq2_k_r4: Zen4 * iq2_k_r4: NEON * iq2_k_r4: better matrix x vector multiplication on NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-17IQ3_K_R4 (#145)Kawrakow
* iq3_k_r4 WIP * iq3_k_r4: Zen4 * iq3_k_r4: AVX2 * iq3_k_r4: NEON * iq3_k_r4: faster matrix x vector multiplication on NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-15BF16_R16 - 16 interleaved bf16 rows (#142)Kawrakow
* Not working bf16_r4 * Adding bf16_r8 Small performance gain compared to bf16 - 258 t/s vs 234 t/s. I guess, this is still sub-obtimal. * bf16_rx: Very slightly faster by interleaving 16 rows 258 t/s -> 263 t/s * Rename bf16_r4 to bf16_r16 We are interleaving 16 rows now. * Cleanup unused stuff --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-14Q8_K_R8: Fastest quantized matrix multiplications (#141)Kawrakow
* q8_k_r8: fastest matrix multiplication known to human kind We get PP-512(LLaMA-3.1-8B) = 370 t/s on a Ryzen-7950X! * q8_k_r8: AVX2 I was worried that we don't have enough vector registrers on AVX2, but it looks like it handles it just fine. We get PP-512(LLaMA-3.1-8B) = 354 t/s on a Ryzen-5975WX. Slightly slower than the Zen4 version with double the threads, but still a huge upgrade compared to Q8_0_R4. * q8_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 159.2 t/s. Compare this to the 128 t/s we have fr Q8_0_R4. * q8_k_r4: go to signed ints Why? * On AVX2 _mm256_maddubs_epi16() may overflow, so we need to stay within the signed int range and use _mm256_sign_epi8. Not yet tested on the AVX2 comp, vut expect major slowdown. * It is almost 10% faster on ARM_NEON. Somehow the veorrq_u8() needed tto convert from unsigned to signed seems to be extremely slow on the M2-Max * We only lose ~0.5% in oerformance on Zen4 (there the exclusive or that we now use to convert fro signed to unsigned seems to be much faster than on M2-Max) * Shutup useless compiler warnings --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-12IQ4_K_R4 (#138)Kawrakow
* iq4_k_r4: WIP * iq4_k_r4: Zen4 and hopefully AVX2 On Zen4 we get PP-512(LLaMA-3.1-8B) = 232.6 t/s, up from 182.2 t/s for iq4_k. Applying the extra shift costs a ~6 performance penalty. * iq4_k_r4: AVX2 PP-512 = 227.60 t/s. The shifts are really costly. * iq4_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 108 t/s, up from 58.2 t/s for iq4_k. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-11Q2_K_R4 (#136)Kawrakow
* q2_k_r4: Zen4 PP-512(LLaMA-3.1-8B) = 256 t/s * q3_k_r4: AVX2 * q2_k_r4: AVX2 We get PP-512(LLaMA-3.1-8B) = 287 t/s. Also cherry-picked the q3_k_r4 AVX2 adaptation that I somehow forgot to push upstream. * q2_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 106.2 t/s. TG-128 is 36.02 t/s, which is ~10% higher than q2_K_S. * Make sure rows per thread are a multiple of 4 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-11Q3_K_R4 (#134)Kawrakow
* q3_k_r4: Zen4 works, but not as good as it should be 238 t/s, so sloghtly slower than q6_k_r4. * q3_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 106.9 t/s. This is 1.93X faster than q3_K_S! --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-10Q5_K_R4 (#132)Kawrakow
* q5_k_r4: WIP * q5_k_r4: Zen4 and AVX2 We get PP-512(LLaMA-3.1-8B) = 248.3 t/s on Zen4. Q5_K_S has PP-512 = 190 t/s. * q5_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 96.1 t/s. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-10Q6_K_R4 (#130)Kawrakow
* Adding q6_k_r4 * q6_k_r4: 1st functional AVX2 version * q6_k_r4: AVX2 and simple Zen4 "Simple" as in processing 4 instead of 8 rows at once. On Zen4 we get PP-512(LLaMA-3.1-8B) = 238.3 t/s vs 195.2 t/s for Q6_K. TG-128 @ 1 thread is 7.94 t/s vs 5.38 t/s for Q6_K. * q6_k_r4: 1st NEON version PP-512(LLaMA-3.1-8B) = 78 t/s vs 57.6 t/s for q6_K. TG-128 is slightly lower rthan q6_K for low number of threads, becomes very slightly better at 8 threads. * q6_k_r4: slightly faster NEON PP-512(LLaMA-3.1-8B) = 83.25 t/s * q6_k_r4: slightly faster Zen4 238.3 t/s -> 243.2 t/s --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-09Q4_K_R4 (#129)Kawrakow
* Something is still wrong * Simply don't see what is wrong * q4_k_r4: finally works on Zen4 I had forgotten to prevent token_embd.weight being quantized with q4_k_r4! * q4_k_r4: AVX2 We get PP-512(LLaMA-3.1-8B) = 267 t/s on a Ryzen-5975WX. This is ~30% better than Q4_K_S. * q4_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 110 t/s. Not quite as good as q4_0_r4, but still a massive improvement compared to he 69 t/s for q4_K. * q4_k_r4: slightly better AVX2 PP-512 goes from 267 t/s to 282 t/s on Ryzen-5975WX * Minor * Minor --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-08Rename iq4_nl_x4 to iq4_nl_r4 (#126)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-06iq2_bn_r4: fastest Bitnet CPU implementation on the planet (#124)Kawrakow
* Adding iq2_bn_r4 This Zen4-only implementation achieves PP-512 = 826 t/s (!!!) for Bitnet-1.58b-3B, up from 620 t/s for iq2_bn. * Make sure rows per thread are a multiple of the number of interleaved rows With this I can run iq2_bn_r4 with 32 threads and this increases PP-512 to 872 t/s. * iq2_bn_r4: 1st shot at NEON PP-512 is already faster than iq2_bn (284 t/s vs 246 t/s for Bitnet-1.58b-3B). TG-128 is ~5% slower. * iq2_bn_r4: NEON PP-512 is now 296 t/s. TG-128 is ~20% faster than iq2_bn for 1 thread, but saturates to about the same 93 t/s at 8 threads. * iq2_bn_r4: Experimenting on NEON The matrix x vvector multiplication is erratic. iq2_bn_r4 is faster at 1, 2, and 4 threads, but saturates to a lower t/s at 8 threads compared to iq2_bn. iq2_bn actually manages 99 t/s at 8 threads and not 93 as I wrore in the last commit. iq2_bn_r4 performance has huge fluctuations at 4 and 8 threads. * Some cleanup * iq2_bn_r4: AVX2 As expected, PP is slightly slower as we just don;t have enough vector registers (690 vs 710 t/s). TG is slightly faster (18.2 vs 16.7 t/s at 1 thread). * iq2_bn_r4: use AVX2 implementation on Zen4 for matrix x vector It is faster - we get 29.6 t/s at 1 thread vs 25.9 t/s for iq2_bn. * iq2_bn_r4: simdify q8_K16 quantization (AVX2) PP-512 becomes 834 t/s and TG-128 now saturates to the same performance as iq2_bn for 4 threads. * iq2_bn_r4: simdify q8_K16 quantization (NEON) PP-512 is now 304.7 t/s, and TG-128 @ 8 threads very slightly outperforms iq2_bn (100.7 t/s vs 99.6 t/s) * iq2_bn_r4: fix AVX2 after breaking it two commits ago * iq2_bn_r4: better AVX2 As we don't have enough vector registers on AVX2, it is better to do two passes per row needing only half of the accumulator registers that way. With this, we now beat iq2_bn PP also on AVX2 by a small margin. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-04IQ4_XS_R4 (#123)Kawrakow
* Adding iq4_xs_r4 This is a 1st working version on Zen4. We get PP-512(LLaMA-3.1-8B) = 226 t/s, so 16% slower than iq4_nl_x4. * iq4_xs_r4: WIP * iq4_xs_r4: Use AVX2 version for matrix x vector on Zen4 * iq4_xs_r4: NEON We get PP-512(LLaMA-3.1-8B) = 115.6 t/s on M2-Max, up from 68.2 t/s for iq4_xs! * DRY --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-03Q6_0_R4 (#122)Kawrakow
* Adding q6_0_r4 We get PP-512(LLaMA-3.1-8B) = 257 t/s on a Ryzen-7950X. * q6_0_r4: NEON We get PP-512(LLaMA-3.1-8B) = 95 t/s on M2-Max. In terms of ops, q6_0_r4 is identical to q5_0_r4 except for loading the high bits being vld1q_u8_x2 instead of vld1q_u8. It is strange that this can make a 5% difference in performance, especially considering that this is amortized (re-used) over 8 columns in the right matrix. Or am I running out of vector registers? * Fix AVX2 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-03Q5_0_R4 (#121)Kawrakow
* Adding q5_0_r4 We get PP-512(LLaMA-3.1-8B) = 256.7 t/s on a Ryzen-7950X. We even get TG-128 improvement to 11.7 t/s from 11.1 t/s. * q5_0_r4: NEON We get PP-512(LLaMA-3.1-8B) = 99.6 t/s on M2-Max, up from 71.0 t/s for Q5_0. The difference to mainline llama.cpp is no longer funny: they get 26.5 t/s for Q5_0. For TG, we are nor able to fully saturate memory bandwidth and arrive at 22.1 t/s @ 8 threads. Mainline llama.cpp gets 20.6 t/s for Q5_0. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-03Q8_0_R4 (#120)Kawrakow
* Adding q8_0_r4 We get PP-512(LLaMA-3.1-8B) = 268 t/s on a Ryzen-7950X compared to 175.6 t/s for Q8_0. * q8_0_r4: NEON We get PP-512(LLaMA-3.1-8B) = 112.6 t/s on M2-Max. * q8_0_r4: Zen4 matrix-vector specialization --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-02Q4_0_R4 (#119)Kawrakow
* Adding iq4_0_r4 - q4_0 repacked We get PP-512(LLaMA-3.1-8B) = 278 t/s on a Ryzen-7950X CPU, so ~5-6% faster than iq4_nl_x4. * q4_0_r4: NEON Here we get 115.8 t/s, so also ~5% better than iq4_nl_x4. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-12-02IQ4_NL_X4 (#118)Kawrakow
* Adding iq4_nl_x4 Looks very promising - I get PP-512(LLaMA-3.1-8B) = 230 t/s on the Ryzen-7950X! This is faster than any other quant and ~40% faster than iq4_nl. * iq4_nl_x4: getting amazing This Zen4 variant gets us to PP-512(LLaMA-3.1-8B) = 263 t/s! * iq4_nl_x4: AVX2 Here we gain only 25% compared to iq4_nl * iq4_nl_x4: NEON On M2-Max we get PP-512(LLaMA-3.1-8B) = 109.7 t/s, up from 82.4 t/s for iq4_nl. * iq4_nl_x4: minor NEON improvement and cleanup This gets us to 110.3 t/s. In comparison, IQ4_NL_4_4 in mainline llama.cpp achieves 92.3 t/s. * iq4_nl_x4: NEON specialization for matrix x vector --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-25Bitnet changes (#106)Kawrakow
* Adapting iq2_bn to work without separate scale tensors Why? It is becoming burdensome to maintain the special Bitnet conversion in convert_hf_to_gguf.py, so I thnk it is better to make iq1_bn and iq2_bn just work with the mainline conversion script (which does not generate scales). * Adapting iq1_bn to work without separate scale tensors * Adapting iq2_bn: CUDA dequantize * Adapting iq2_bn: CUDA works * Adapting iq1_bn: CUDA works * Adapting iq1_bn, iq2_bn: NEON * Adapting iq1_bn, iq2_bn: Metal Dequantize works, but there is still something wrong with the dot products. * WIP Absoolutely don't see what is wrong with the iq1_bn and iq2_bn vector dot product kernels. * Remove iq1_tn and iq2_tn - Part 1 Now that iq1_bn and iq2_bn have per row scales, there is no reason to also have iq1_tn and iq2_tn. * Remove iq1_tn and iq2_tn - Part 2 * Bitnet: use the standard llm_build_kv to build self attention My main motivation was to enable FA. But FA does not work anyway because head size is 100 for the Botnet ternary models (and I had forgotten this little detail). * Revert "Avoid rebuild of GGML graph for each token (#98)" This reverts commit f2d315b46f7aacc7df4b86bd8acba387b30e11ca. As far as I can tell, the commit breaks Metal TG. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-18CLI - Specify GGML_TYPE to quantize for the main tensors. (#91)Nexes the Elder
To complement the token_embd.weight and output.weight : attn_v.weight attn_k.weight. attn_q_weight attn_output.weight attn_qkv.weight ffn_gate ffn_down ffn_up
2024-10-16Adding IQ4_KSS: 4.0 bpw quants (#89)Kawrakow
* iq4_kss: WIP * iq4_kss: CUDA dequantize works So we can run perplexity. Sadly, the result does not look good on the bpw vs quantization error plot. * iq4_kss: slightly better quantization * iq4_kss: another small quantization improvement * iq4_kss: CUDA works TG-128 performance is very decent with 131 t/s for LLaMA-3.1-8B. In comparison, we have 123 t/s for q4_0 and 128 t/s for iq4_ks. I.e., the reduced model size more than offsets the additional bit fiddling required for iq4_kss. * iq4_kss: new bit arrangement - CUDA and Zen4 work Did not lose performance on CUDA. Zen4 is decent, but not great: PP-512(LLaMA-3.1-8B) = 163 t/s. TG-128 is of course better than other 4-bit quants due to smaller model size. We get 14.5 t/s @ 8 threads. * iq4_kss: ARM_NEON. Predictably very slow * iq4_kss: Metal PP is not too bad - just 10% slower than q4_0. But TG is 30% slower, i.e., predictably bad. * iq4_kss: somewhat faster Metal dot product 45.75 t/s -> 48.75 t/s. Still 22% slower than q4_0 * iq4_kss: AVX2 Bad, but better than I expected. PP-512(LLaMA-3.1-8B) = 167 t/s on the Ryzen-5950X. I.e., with 32 AVX2 threads we get the performance of 16 Zen4 threads. * iq4_kss: very slightly faster Metal dot product 48.7 t/s -> 49.3 t/s --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-13IQ2_KS: 2.1875 bpw non-linear quantization (#85)Kawrakow
* Experimenting * iq2k: Try make_qx_quants for the scale Slightly better for LLaMA-3.1, Gemma-2, slightly worse for Qwen2.5 * iq2k with make_qx_quants: adjust scale * iq2ks: basics * iq2_ks: CUDA works * iq2_ks: WIP * iq2_ks: WIP * iq2_ks: Zen4 * iq2_ks: AVX2 * iq2_ks: scalar dot product * iq2_ks: ARM_NEON * iq2_ks: Metal * iq2_ks: faster Metal LLaMA-3.1-8B: PP-512 = 475.22 ± 0.37 t/s TG-128 = 45.32 ± 0.03 t/s --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-09New SOTA quantization: 4.25 bpw IQ4_KS (#83)Kawrakow
* iq4_k_xxs: basics * WIP + adding iq3_kl quantization mix * iq4_xxs: this looks very viable compared to iq4_xs At the same 4.25 bpw PPL is always better, for some models significantly better. I'll rename to iq4_ks and keep it. * iq4_xxs: CUDA dot product We get TG-128 = 126 t/s for LLaMA-3.1-8B, compared to 123 t/s for q4_0. * iq4_xxs: scalar CPU dot product Also fix the breakage I caused with the dedicated work buffer quantization portion when the multiplication is not done via iqk_mul_mat. * iq4_xxs: Zen4 I noticed that iq4_xs is wrong on Zen4 (and possibly AVX2). Again the same mistake of packing int32_t back to int16_t, which overflows occasionally (just occasionally, that's why the result doesn't look completely wrong, so I didn't notice). * Fix iq4_xs (Zen4) * iq4_xxs: AVX2 * iq4_xxs: ARM_NEON * iq4_xxs: Metal * iq4_xxs: slightly faster TG on Metal * iq4_xxs: rename to iq4_ks After all, tt is a smaller variant of iq4_k. * iq3_kl: use iq4_ks instead of iq4_k/iq4_xs --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-02Adding Q6_0 (#77)Kawrakow
* Adding q6_0 - basics + AVX2/Zen4 working * Adding q6_0: CUDA dequantize works, but not mmvq * Adding q6_0: CUDA mmvq works * Adding q6_0: CUDA cpy, so Q6_0 can be used for KV-cache * Add q6_0 to CPU flash attention Disappointing result: for LlaMA-3.2-1B, q6_0 K- and V-cache gives about the same PPL as q8_0 K-cache and q4_0 V-cache, while needing the exact same RAM. I.e., what was the point? * q6_0: slightly better kv-cache result Better than q8_0+q4_0, but not as good as q8_0+iq4_nl * q6_0: works on ARM_NEON * q6_0: dequantize works on Metal, but not vector dot product * q6_0: it now works on Metal Outperforms q5_0 by a significant margin. E.g. | model | size | params | backend | ngl | threads | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | ------------: | ---------------: | | llama 8B Q6_0 | 6.08 GiB | 8.03 B | Metal | 100 | 4 | tg128 | 44.02 ± 0.08 | | llama 8B Q5_0 | 5.21 GiB | 8.03 B | Metal | 100 | 4 | tg128 | 40.13 ± 0.12 | | llama 8B Q6_0 | 6.08 GiB | 8.03 B | Metal | 100 | 4 | pp512 | 500.55 ± 0.32 | | llama 8B Q5_0 | 5.21 GiB | 8.03 B | Metal | 100 | 4 | pp512 | 448.02 ± 0.27 | * q6_0: can now be used for kv-cache on Metal --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-09-27Adding ability to have meta data per tensor row (#61)Kawrakow
* POC: per row scale This is a POC how to work around opinionated ggml to have scales per row rather than per block. Only implemened for Zen4 and only for iq2_tn. * POC per row scale: iq2_tn on NEON * POC per row scale: iq2_tn on Metal * Per row scale Metal templates * iq1_tn: shrink to 1.625 bpw (NEON and Metal) * POC per row scale: CUDA * POC per row scale: add CUDA TODOs There are two places in ggml-cuda.cu left where it is assumed that type_size * n_per_row / block_size is the way to compute and handle row sizes. This does not affect simple usage, but will lead to issues when tensors are split between GPUs. * Per row scales - CUDA The only place left where there are unnecessary assumptions being made is in the Flash Attention code. As we are not using any quants that use per row scales for quantized KV cache, it should be OK for now. * Update IQ1_TN and IQ2_TN bpw shown to user --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-09-09Adding IQ1_TN - 1.6875 bpw for TriLM ternary models (#44)Kawrakow
* Adding iq1_tn - 1.6875 bpw for TriLM ternary models * iq1_tn: NEON * iq1_tn: faster NEON * iq2_bn: improve performance on NEON We now get TG-128 = 100 t/s for Bitnet-3B-1.58b! * iq1_tn: improve AVX2 PP-512 goes to 533 t/s up from 455. TG-128 @ 2 threads goes to 16.6 t/s up from 14.2. However, we seem to have a bottleneck somewhere as TG saturates at 8 threads. * iq1_tn: improve Zen4 PP-512 goes to 485 t/s up from 352. With FA we get 545 t/s up from 380. TG-128 @ 1 thread goes to 12.4 t/s up from 10.4. However, we seem to have a bottleneck somewhere as TG saturates at 8 threads. * iq2_bn: improve on Zen4 We now get PP-512 = 614 t/s up from 542 t/s * iq2_bn: improve AVX2 implementation We now get PP-512 = 753 t/s up from 680 t/s. * Remove unnecessary barrier in ggml_compute_forward_mul_mat --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-08-12Merge mainline - Aug 12 2024 (#17)Kawrakow
* Merge mainline * Fix after merge * Remove CI check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-08-09iq6_k: WIP (quantize/dequantize)Iwan Kawrakow
2024-08-07Adding IQ2_TN for use with ternary models (#13)Kawrakow
* iq2_tn: TriLM specific 2.0625 bpw quantization Quantize/dequantize/scale dot product. I get 46 t/s for the TriLM-3.9B with any SIMD! Finally a compiler doing a decent job auto-vectorizing the scalar implementation. * iq2_tn: AVX512 Just reusing the k-quants template gets us to PP-512 = 376 t/s, TG-128 = 47.6 t/s for TriLM-3.9B. * iq2_tn: AVX512 With this tweak we get to PP-512 = 431 t/s. * iq2_tn: AVX512 With this tweak we get TG-128 = 19.58 / 35.18 t/s for 1 / 2 threads. At 4 threads we saturate at 48.41 t/s, and then performance slowly degrades with increasing number of threads. * iq2_tn: AVX2 PP512 = 440 t/s on the Ryzen-5975WX. We should be able to do better. * iq2_tn: initial NEON version * iq2_tn: NEON For TriLM-3.9B running on the M2-Max we get PP-512 = 193.5 t/s, TG-128 = 75.5 t/s. This is in line with what we have for iq2_bn ant 3.3B Bitnet. * iq2_tn: Metal For TriLM-3.9B on a 30-core M2-Max we get PP-512 = 890 t/s, TG-128 = 98.5 t/s. * iq2_tn: CUDA For TriLM-3.9B running on RTX-4080 we get PP-512 = 9936 t/s, TG-128 = 299.2 t/s. * iq2_tn: AVX2 PP improvement We now get PP-512 = 490.73 t/s for TriLM-3.9B on the Ryzen-5975WX. We have PP-512 = 636.61 t/s for Bintnet-3B quantized with iq2_bn. Bintnet-3B is actually 3.4B, TriLM-3.9B is 3.99B, so we would expect 3.43/3.99 * 636 = 546 t/s, so it seems we still have something that is not quite optimal in iq2_tn. * iq2_tn: small NEON improvement For TriLM-3.9B we now get PP-512 = 206.6 t/s and TG-128 = 76.4 t/s. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-08-05q2_K: allow it to detect ternary nets and quantize accordinglyIwan Kawrakow
2024-08-01iq3_k: BasicsIwan Kawrakow
Quantize/dequantize, CUDA dequantize. PPL of LLaMA-3.1-8B is better than iq3_s and iq3_m.
2024-08-01iq5_k: BasicsIwan Kawrakow
Quantize/dequantize, CUDA dequantize
2024-08-01iq2_k: BasicsIwan Kawrakow
Quantize/dequantize, CUDA deqantize, AVX512 iqk_mul_mat.
2024-07-28IQ4_K: SOTA 4-bit quantization (#6)Kawrakow
* iq4_k: basics * quantize/dequantize works * CUDA dequantize works and one can run PPL calcs. I get PPL = 6.5258 for LlaMA-3.1-8B, which is 1.77% above fp16. In comparison, q4_K_S (same size) is 2.88% above fp16. * TG on CUDA does not work. Johannes has changed the way i-quant dot products are done, so need to sort out what he had in mind * iqk_mul_mat is not implemented. * iq4_k: TG now works on CUDA * iq4_k: AVX512 implementation For LLaMA-3.1-8B we get PP-512 = 182.6 t/s, TG-128 = 13.6 t/s, so almost the same as q4_K_S. * iq4_k: AVX2 implementation For LLaMA-3.1-8B we get PP-512 = 203.1 t/s, TG-128 = 12.9 t/s on the Ryzen-5975X. * iq4_k: NEON implementation For LLaMA-3.1-8B we get PP-512 = 60.7 t/s, TG-128 = 25.0 t/s on the M2-Max. TG is on par with q4_K_S, PP is ~10% slower. * iq4_k: Metal implementation For LLaMA-3.1-8B we get PP-512 = 445 t/s, TG-128 = 46.3 t/s on a 30-core M2-Max GPU. This is to be compared with (currently) PP-512 = 460 t/s, TG-128 = 51 t/s for q4_K_S. * iq4_k: scalar dot product --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-07-27Merge mainline llama.cpp (#3)Kawrakow
* Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-06-24Bitnet: tiny bity faster 1.625 bpw variant on MetalIwan Kawrakow
We get 70.7 t/s for TG-128 vs 69.5 t/s before.
2024-06-22bitnet: add 2 bpw quantizationIwan Kawrakow
The scalar dot product already chieves 37 t/s for TG!
2024-06-22bitnet: CUDA, scalar, AVX2Iwan Kawrakow
2024-06-13`build`: rename main → llama-cli, server → llama-server, llava-cli → ↵Olivier Chafik
llama-llava-cli, etc... (#7809) * `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew * server: update refs -> llama-server gitignore llama-server * server: simplify nix package * main: update refs -> llama fix examples/main ref * main/server: fix targets * update more names * Update build.yml * rm accidentally checked in bins * update straggling refs * Update .gitignore * Update server-llm.sh * main: target name -> llama-cli * Prefix all example bins w/ llama- * fix main refs * rename {main->llama}-cmake-pkg binary * prefix more cmake targets w/ llama- * add/fix gbnf-validator subfolder to cmake * sort cmake example subdirs * rm bin files * fix llama-lookup-* Makefile rules * gitignore /llama-* * rename Dockerfiles * rename llama|main -> llama-cli; consistent RPM bin prefixes * fix some missing -cli suffixes * rename dockerfile w/ llama-cli * rename(make): llama-baby-llama * update dockerfile refs * more llama-cli(.exe) * fix test-eval-callback * rename: llama-cli-cmake-pkg(.exe) * address gbnf-validator unused fread warning (switched to C++ / ifstream) * add two missing llama- prefixes * Updating docs for eval-callback binary to use new `llama-` prefix. * Updating a few lingering doc references for rename of main to llama-cli * Updating `run-with-preset.py` to use new binary names. Updating docs around `perplexity` binary rename. * Updating documentation references for lookup-merge and export-lora * Updating two small `main` references missed earlier in the finetune docs. * Update apps.nix * update grammar/README.md w/ new llama-* names * update llama-rpc-server bin name + doc * Revert "update llama-rpc-server bin name + doc" This reverts commit e474ef1df481fd8936cd7d098e3065d7de378930. * add hot topic notice to README.md * Update README.md * Update README.md * rename gguf-split & quantize bins refs in **/tests.sh --------- Co-authored-by: HanClinto <hanclinto@gmail.com>
2024-06-04common : refactor cli arg parsing (#7675)Georgi Gerganov
* common : gpt_params_parse do not print usage * common : rework usage print (wip) * common : valign * common : rework print_usage * infill : remove cfg support * common : reorder args * server : deduplicate parameters ggml-ci * common : add missing header ggml-ci * common : remote --random-prompt usages ggml-ci * examples : migrate to gpt_params ggml-ci * batched-bench : migrate to gpt_params * retrieval : migrate to gpt_params * common : change defaults for escape and n_ctx * common : remove chatml and instruct params ggml-ci * common : passkey use gpt_params
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-17 15:46:05 +0000