vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1298 commits 380 branches 3056 tags 365 MiB
Commit graph

1298 commits

This branch
This branch
All branches
Author SHA1 Message Date
slaren
5659391b6a remove duplicated ctx/model functions 
ggml-ci
 2023-09-28 19:36:16 +02:00
slaren
65b83f37bd Merge remote-tracking branch 'origin/master' into llama-model-params 2023-09-28 19:13:59 +02:00
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
Kevin Ji
45855b3f1c
docs : mark code as Bash (#3375) 2023-09-28 09:11:32 -04:00
Pierre Alexandre SCHEMBRI
4aea3b846e
readme : add Mistral AI release 0.1 (#3362) 2023-09-28 15:13:37 +03:00
slaren
da0400344b
ggml-cuda : perform cublas fp16 matrix multiplication as fp16 (#3370)
Some checks failed
Code Coverage / run (push) Has been cancelled
Details 
* ggml-cuda : perform cublas fp16 matrix multiplication as fp16

* try to fix rocm build

* restrict fp16 mat mul to volta and up
 2023-09-28 13:08:28 +03:00
Zhang Peiyuan
e519621010
convert : remove bug in convert.py permute function (#3364) 2023-09-27 20:45:20 +02:00
Richard Roberson
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290) 
* Resync my fork with new llama.cpp commits

* examples : rename to use dash instead of underscore

* New model conversions

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-09-27 19:25:12 +03:00
Cebtenzzre
20c7e1e804
gguf : fix a few general keys (#3341) 2023-09-27 12:18:07 -04:00
Rickard Hallerbäck
dc6897404e
metal : reusing llama.cpp logging (#3152) 
* metal : reusing llama.cpp logging

* cmake : build fix

* metal : logging callback

* metal : logging va_args memory fix

* metal : minor cleanup

* metal : setting function like logging macro to capital letters

* llama.cpp : trailing whitespace fix

* ggml : log level enum used by llama

* Makefile : cleanup ggml-metal recipe

* ggml : ggml_log_callback typedef

* ggml : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-09-27 18:48:33 +03:00
Jag Chadha
527e57cfd8
build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (#3342) 2023-09-27 18:34:32 +03:00
BarfingLemurs
ffe88a36a9
readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (#3340) 
* Update README.md

* Update README.md

* Update README.md with k-quants bpw measurements
 2023-09-27 18:30:36 +03:00
slaren
8f5b0eaa8a llama.cpp : add llama_get_model 
common : add llama_tokenize from model
 2023-09-26 23:23:59 +02:00
DAN™
99115f3fa6
cmake : fix build-info.h on MSVC (#3309) 2023-09-25 18:45:33 -04:00
2f38b454
1726f9626f
docs: Fix typo CLBlast_DIR var. (#3330) 2023-09-25 20:24:52 +02:00
Erik Scholz
a98b1633d5
nix : add cuda, use a symlinked toolkit for cmake (#3202) 2023-09-25 13:48:30 +02:00
slaren
0e9ed7f84f main : fix rope freq/scale warning 2023-09-24 01:18:22 +02:00
slaren
c091cdfb24
llama-bench : add README (#3317) 
* llama-bench : add README

* minor edit
 2023-09-23 21:48:24 +02:00
slaren
e5afe4204c llama-bench fix 2023-09-23 14:55:58 +02:00
Cebtenzzre
51a7cf5c6e
examples : fix RoPE defaults to match PR #3240 (#3315) 2023-09-23 12:28:50 +03:00
Kevin Ji
bedb92b603
scripts : use /usr/bin/env in shebang (#3313) 2023-09-22 23:52:23 -04:00
slaren
3469684177 add documentation about --threads-batch to the READMEs 2023-09-23 02:45:05 +02:00
slaren
a6084cc719 add n_threads_batch to system info, refactor to get_system_info() 2023-09-23 02:29:39 +02:00
slaren
92fb8ab5a7 remove low-vram option 2023-09-22 17:34:02 +02:00
slaren
ceb18e44db remove kv_size(), cuda scratch fixes 2023-09-22 03:37:28 +02:00
slaren
d41b53ca7b fix mpi build 2023-09-22 00:58:45 +02:00
slaren
7f95379295 move n_threads to llama_context_params, add n_threads_batch 2023-09-22 00:00:55 +02:00
slaren
96f6dcdeae llama-bench : keep the same model between tests when possible 2023-09-21 21:41:05 +02:00
Lee Drake
bc9d3e3971
Update README.md (#3289) 
* Update README.md

* Update README.md

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2023-09-21 21:00:24 +02:00
slaren
f28e4953a8 fix freq_base/scale default to model value 2023-09-21 20:20:42 +02:00
slaren
39f4afac20 fix metal build 2023-09-21 20:15:22 +02:00
shibe2
36b904e200
ggml-opencl.cpp: Make private functions static (#3300) 2023-09-21 14:10:26 -04:00
slaren
cf1f80596d llama.cpp : split llama_context_params into model and context params 
ggml-ci
 2023-09-21 19:32:04 +02:00
Edward Taylor
324f3403d5
zig : fix for updated c lib (#3259) 2023-09-21 12:08:20 +03:00
yuiseki
f56c418ab0
embedding : update README.md (#3224) 2023-09-21 11:57:40 +03:00
Johannes Gäßler
8185710a80
CUDA: use only 1 thread if fully offloaded (#2915) 2023-09-21 11:43:53 +03:00
Georgi Gerganov
7eb41179ed
readme : update hot topics 2023-09-20 20:48:22 +03:00
Cebtenzzre
a5661d7e71
llama : allow gguf RoPE keys to be overridden with defaults (#3240) 2023-09-20 12:12:47 -04:00
Cebtenzzre
65c2c1c5ab
benchmark-matmult : do not use integer abs() on a float (#3277) 2023-09-20 12:06:08 -04:00
kang
80834daecf
flake : Restore default package's buildInputs (#3262) 2023-09-20 15:48:22 +02:00
Alon
a40f2b656f
CI: FreeBSD fix (#3258) 
* - freebsd ci: use qemu
 2023-09-20 14:06:36 +02:00
Georgi Gerganov
d119c04c15
examples : fix benchmark-matmult (#1554) 
The precision for Q4_0 has degraded since #1508
 2023-09-20 10:02:39 +03:00
Cebtenzzre
8781013ef6
make : restore build-info.h dependency for several targets (#3205) 2023-09-18 10:03:53 -04:00
Erik Scholz
7ddf185537
ci : switch cudatoolkit install on windows to networked (#3236) 2023-09-18 02:21:47 +02:00
Johannes Gäßler
ee66942d7e
CUDA: fix peer access logic (#3231) 2023-09-17 23:35:20 +02:00
Johannes Gäßler
111163e246
CUDA: enable peer access between devices (#2470) 2023-09-17 16:37:53 +02:00
slaren
8b428c9bc8
llama.cpp : show model size and BPW on load (#3223) 2023-09-17 14:33:28 +02:00
Johannes Gäßler
578d8c8f5c
CUDA: fix scratch malloced on non-main device (#3220) 2023-09-17 14:16:22 +02:00
IsaacDynamo
b541b4f0b1
Enable BUILD_SHARED_LIBS=ON on all Windows builds (#3215) 2023-09-16 19:35:25 +02:00
Vlad
5dbc2b3213
Enable build with CUDA 11.0 (make) (#3132) 
* CUDA 11.0 fixes

* Cleaner CUDA/host flags separation

Also renamed GGML_ASSUME into GGML_CUDA_ASSUME
 2023-09-16 16:55:43 +02:00