llama.cpp/examples/perplexity
Georgi Gerganov ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
* tests : verify that RoPE is "additive"

* llama : replace ggml_diag_mask_inf with ggml_add (custom -inf mask)

* ggml : ggml_rope now takes a vector with positions instead of n_past

* metal : add rope_f16 kernel + optimize cpy kernels

* llama : unified KV cache + batch inference API

* llama : add new llama_decode() API that works with llama_batch

* llama : add cell_max heuristic for more efficient kv_cache

* llama : extend llama_kv_cache API

* llama : more robust cell_max heuristic + wip shift

* metal : disable concurrency optimization

* llama : add llama_kv_cache_shift_seq + no more context swaps

* llama : apply K-cache roping for Falcon and Baichuan

* speculative : fix KV cache management

* parallel : example for serving multiple users in parallel

* parallel : disable hot-plug to avoid cache fragmentation

* fixes : speculative KV cache + llama worst-case graph

* llama : extend batch API to select which logits to output

* llama : fix worst case graph build

* ggml-cuda : update rope implementation for parallel decoding (#3254)

* ggml-cuda : update rope implementation for parallel decoding

* better solution for p0 computation

* fix rope

* simpler rope implementation

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* make : add parallel to build + fix static functions in llama.cpp

* simple : fix token counting

* parallel : various improvements

* llama : fix cell_max logic + rename functions

* parallel : try smaller batches when the KV cache is fragmented

* parallel : fix sequence termination criteria

* llama : silence errors KV cache errors

* parallel : remove new line from prompt

* parallel : process system prompt once + configurable paramters + llama API

* parallel : remove question with short answers

* parallel : count cache misses

* parallel : print misses on each request

* parallel : minor

* llama : fix n_kv to never become 0

* parallel : rename hot-plug to continuous-batching

* llama : improve llama_batch API + simplify parallel example

* simple : add parallel decoding support

* simple : improve comments + free batch

* ggml-cuda : add rope f16, restore performance with parallel decoding (#3272)

* ggml-cuda : add rope f16, restore performance

* offload KQ_mask with all models

* fix rope shift

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* llama : disable MPI for now

ggml-ci

* train : make KQ_pos memory buffer permanent via dummy scale op

* ggml : revert change to ggml_cpy, add ggml_cont_Nd instead (#3275)

ggml-ci

* parallel : fix bug (extra BOS) + smaller token_prev array

* parallel : fix cases where the input prompts can overflow the batch

* parallel : add disabled experimental batch chunking in powers of two

* llama : llama.h formatting + comments

* simple : add README.md

* llama : fix kv cache heuristic when context is less than 32

* parallel : fix crash when `-n -1`

* llama : simplify returns if/else branches

* metal : use mm kernels for batch size > 2

* examples : utilize new llama_get_logits_ith()

* examples : add example for batched decoding

* examples : do not eval prompt 2 times (close #3348)

* server : clear the KV cache beyond n_past before llama_decode

* server : avoid context swaps by shifting the KV cache

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-09-28 19:04:36 +03:00
..
CMakeLists.txt cmake : install targets (#2256) 2023-07-19 10:01:11 +03:00
perplexity.cpp llama : custom attention mask + parallel decoding + no context swaps (#3228) 2023-09-28 19:04:36 +03:00
README.md readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (#3340) 2023-09-27 18:30:36 +03:00

perplexity

TODO

Llama 2 70B Scorechart

Quantization Model size (GiB) Perplexity Delta to fp16
Q4_0 36.20 3.5550 3.61%
Q4_1 40.20 3.5125 2.37%
Q5_0 44.20 3.4744 1.26%
Q2_K 27.27 3.7339 8.82%
Q3_K_S 27.86 3.7019 7.89%
Q3_K_M 30.83 3.5932 4.72%
Q3_K_L 33.67 3.5617 3.80%
Q4_K_S 36.39 3.4852 1.57%
Q4_K_M 38.54 3.4725 1.20%
Q5_K_S 44.20 3.4483 0.50%
Q5_K_M 45.41 3.4451 0.40%
Q6_K 52.70 3.4367 0.16%
fp16 128.5 3.4313 -