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>
* iq1_bn: improve CUDA TG
On RTX-3080 TG-128(Bitnet-1.58b-3B) goes from 318 t/s to 340 t/s.
I see I have on the front page 301 t/s, so pretty nice improvement
since then.
* iq2_bn(CUDA): quants are not 4-byte aligned
---------
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>
* Added Johannes' changes, still getting NaNs with quantized k-cache.
Also getting NaN's on Johannes's mainline branch.
* This fixes it
---------
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>
* Enable IQ4_NL for V-cache in token generation
* We don't need these
* Update printour of allowed quantized KV-cache combinations
* Add IQ4_NL + IQ4_NL to FA
This is a better alternative than Q4_0 + Q4_0 for the VRAM poor.
* Remove file added by mistake
* Fix typo, which is not really a bug
---------
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>
* iq3_k: fix Metal dot product
I was accessing the scales as 4-byte aligned, but iq3_k is
not 4-byte aligned. Instead of throwing an error (as it happens
on CUDA when one makes this mistake), Metal silently accepts
and we get garbage.
* iq3_k: slightly faster Metal dot product
---------
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>
* Do not quantize activations if not necessary
* Do not quantize activations if not necessary also for MoE models
---------
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>
When I changed iqk_mul_mat to use type-1 dot products for type-0
legacy quants, I forgot to also change the vec_dot_type when
the dot product is done via ggml as in flash attention.
This commit fixes it.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Be able to use IQ4_NL for KV cache on AVX2/Zen4
* Be able to use IQ4_NL for KV cache on ARM_NEON
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2
PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up
from 133.2 t/s.
* Speed up float -> iq4_nl conversion on CUDA
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2
PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up
from 133.2 t/s.
* Fix AVX2
In addition to fixing iq4_nl, it seems I never adhusted the AVX2
implementation for iq2_tn to the block scale removal?
This commit also fixes that.
---------
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>
* Fix C++ compilation warnings caused by ggml-common.h
* Disable c99-extensions warning
I get tons of those on macOS due to the arm_neon.h header.
* Disable c99-extensions warning only for APPLE
* Fix warnings in iqk_quantize.cpp
Also add GGML_ABORT when implementation is missing.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
It looks like ArmV8 ISA has support for bf16, but my M2 Max
does not have it, so resorting to bf16 -> f32 conversion and
computations in f32. This is 2x slower than f16, but 8x better
compared to what I get if I try to run a bf16 model on the M2
(NEON and Metal).
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
