nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/examples
History
Kawrakow e885c1e59b Q8_K_R8: Fastest quantized matrix multiplications (#141) 
* 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>
 		2024-12-14 09:24:30 +01:00
..
baby-llama Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
batched Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
batched-bench Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
batched.swift Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
benchmark `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
convert-llama2c-to-ggml `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
cvector-generator Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
deprecation-warning Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
embedding Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
eval-callback Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
export-lora Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
gbnf-validator Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
gguf Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
gguf-hash Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
gguf-split `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
gritlm llama : allow pooled embeddings on any model (#7477) 2024-06-21 08:38:22 +03:00
imatrix Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
infill Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
jeopardy `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
llama-bench Adding Q6_0 (#77) 2024-10-02 15:22:13 +03:00
llama.android Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
llama.swiftui Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
llava Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
lookahead Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
lookup Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
main Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
main-cmake-pkg Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
parallel Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
passkey Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
perplexity Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
quantize Q8_K_R8: Fastest quantized matrix multiplications (#141) 2024-12-14 09:24:30 +01:00
quantize-stats Adding IQ4_KSS: 4.0 bpw quants (#89) 2024-10-16 15:18:26 +03:00
retrieval Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
rpc Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
save-load-state Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
server Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
simple Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
speculative Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
sycl Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
tokenize Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
CMakeLists.txt Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
Miku.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
base-translate.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
chat-13B.bat Create chat-13B.bat (#592) 2023-03-29 20:21:09 +03:00
chat-13B.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
chat-persistent.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
chat-vicuna.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
chat.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
convert_legacy_llama.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
json_schema_pydantic_example.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
json_schema_to_grammar.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
llama.vim llama.vim : added api key support (#5090) 2024-01-23 08:51:27 +02:00
llm.vim llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) 2023-08-30 09:50:55 +03:00
pydantic_models_to_grammar.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
pydantic_models_to_grammar_examples.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
reason-act.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
regex_to_grammar.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
server-llama2-13B.sh `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
server_embd.py Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
ts-type-to-grammar.sh JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) 2024-04-12 19:43:38 +01:00