* 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>
* 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>
* 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>
* 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>
* 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>
* 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>
* multi_sdd: WIP
* multi_sdd: CPU works
* multi_add: CUDA
* multi_add: simplify
* multi_add: Metal
* Metal: speed up mul_mat_id
For the Granite-1B MoE model PP-512 goes from
156 t/s to 890 t/s, so nearly a 6X speedup!
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
I had forgotten that build_bitnet() does not use the standerd
llm_build_ffn function, so the fused mul-silu didn't get used
for Bitnet when I added it to llm_build_ffn.
This gives us another ~1% speedup for TG-128.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* 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 f2d315b46f.
As far as I can tell, the commit breaks Metal TG.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Add Granite and GranoteMoE models
* Granite: avoid NaNs on CUDA by scaling Q before K*Q multiplication
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Introduces caching of GGML graph to avoid unnecessary full rebuild between each token.
KV cache parameters, which change with each token, are updated directly in cached GGML
graph. Can be disabled with GGML_DISABLE_GRAPH_CACHING environment variable.
* attn_q Q4 & attn_v Q6 for Llama 3.1 Q5_K_S
Pattern worth to be tested on more quants and on L3 8B.
PPL 512 = -0.024 for 70b ; - 0.005 for 8b
Size = - 640MiB for 70b ; - 64MiB for 8b
70b Q5_K_S now beats Q5_K_M by -0.012 ppl
I suspect that it goes for L3 as well, which was quite insensitive to attn_q quantization.
* indent
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
* 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>
* 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>
* Adding fused y*unary(x) op
* Fused y*unary(x) op: CUDA
* Fused y*unary(x) op: dedicated CPU implementation for silu and gelu
* Fused y*unary(x) op: Metal
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* 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>
On the CPU I get the exact same PPL with and without FA
using bf16 for kv-cache. But on CUDA the bf16 kv-cache
result is about the same as the fp16 kv-cache CPU result,
so I'm missing some conversion somewhere.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
In this way we can avoid the Q, K, V copies being made
after multiplication with the QKV tensor in, e.g., Phi-3.5-mini.
This results in a 6-7% speedup of PP-512(Phi-3.5-mini)
on CUDA (RTX-4080)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Adding GGML_UNARY_OP_SWIGLU
This commit implements the ggml op and CPU compute
forward. I see ~3-4% speedup of PP-512 for Phi-3.5-mini.
* GGML_UNARY_OP_SWIGLU: CUDA implementation
I observe ~12% speedup for PP-512(Phi-3.5-mini).
* GGML_UNARY_OP_SWIGLU: Metal implementation
We get ~2% speedup for PP-512(Phi-3.5-mini).
* GGML_UNARY_OP_SWIGLU: minor improvement on Metal
* GGML_UNARY_OP_SWIGLU: cleanup
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* 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>
* Some tweaks for i-quants
Improve Gemma2 PPL while reducing size
* Some tweaks for iq2_k and iq3_k
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* 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>
* soft_cap_max: initial CPU version of fused softcap + soft_max
With this vanilla CPU implementation I'm already getting a ~3% speedup
for Gemma-2-9b and a prompt of 8192 tokens.
* soft_cap_max: WIP - something is wrong with CUDA
* soft_cap_max: looks good on CPU and CUDA
* Add softcap to flash attention
Just CPU and CUDA for now (but, as we know, flash attention
on the CPU is useless in llama.cpp).
On CUDA this improves PP performance quite a bit, especially for
long contexts. E.g., for PP-16384, I now get 3777 t/s.
Without this change, one cannot use FA, and one gets 2300 t/s
(after fusing softcap and softmax), or 2000 t/s without the
fused softcap+softmax.
In comparison, mainline llama.cpp has PP-16384 = 1549 t/s before
PR-8542 (where Johannes Gaessler has also added softcap to FA),
and PP-16384 = 3097 t/s after this PR.
* soft_cap_max: Metal
* Flash attention with softcap: Metal
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Softcap: WIP
Fuses scale + tanh + scale as used for softcaping in some
models.
Just CPU for now. ~1.4% for PP-512 on Gemma2-9b, no effect on TG.
Somewhat surprisingly the improvement does not increase as I
go to longer contexts. Gemma2 does softcap on K*Q, which grows
quadratically with context length, so I would have thought
the benefit from fusing scale, tanh, scale would increase.
But no, no luck.
* softcap: CUDA
* softcap: CUDA
~1% speedup for Gemma2-9b
* softcap: Metal and NEON
About 1% speedup.
* Simdified gelu
Gives ~1% speedup for Gemma2-9b prompt processing on AVX512/AVX2.
It looks like the gelu operation is memory bound on my CPU's
after SIMD-ifying it. By not using the 128 kb gelu lookup table
we gain a small advantage.
On the M2-Max the lookup table is slightly faster than the SIMD
version, so left the lookup table for ARM_NEON.
* softcap, tanh: avoid NaNs for large arguments (AVX2, AVX512)
Not that I have encountered this in practice, but just to be sure.
This does it for AVX512 and AVX2, still need a guard for ARM_NEON.
* llama-bench: add ability to turn off warmup runs
So we don't need to wait forever on, e.g., benchmarks involving
long contexts.
* softcap, tanh: avoid NaNs for large arguments (NEON)
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
For LLaMA-3.1 models:
* It is better to quantize all of attn_v with iq3_k instead of
half of attn_v with iq4_k
* Quantizing attn_output with iq3_k results in a larger PPL decrease
compared to what one expects from the added bpw.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* 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>
* 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>
* 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>
