Georgi Gerganovandslaren b0f27361f3 sampling : avoid expensive softmax during greedy sampling (#9605) ...

* sampling : avoid expensive softmax during greedy sampling

ggml-ci

* speculative : fix default RNG seed + set sparams.n_probs

* Update tests/test-sampling.cpp

Co-authored-by: slaren <[email protected]>

* sampling : add clarifying comment [no ci]

---------

Co-authored-by: slaren <[email protected]>

2024-09-24 09:03:17 +03:00

..

.gitignore

tests : gitignore ggml-common.h

2024-03-09 14:17:11 +02:00

CMakeLists.txt

threadpool : skip polling for unused threads (#9461)

2024-09-17 11:19:46 +03:00

get-model.cpp

…

get-model.h

…

run-json-schema-to-grammar.mjs

json-schema-to-grammar improvements (+ added to server) (#5978)

2024-03-21 11:50:43 +00:00

test-arg-parser.cpp

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

test-autorelease.cpp

…

test-backend-ops.cpp

CUDA: enable Gemma FA for HIP/Pascal (#9581)

2024-09-22 09:34:52 +02:00

test-barrier.cpp

threadpool : skip polling for unused threads (#9461)

2024-09-17 11:19:46 +03:00

test-c.c

…

test-chat-template.cpp

tests : fix printfs (#8068)

2024-07-25 18:58:04 +03:00

test-double-float.cpp

ggml : minor naming changes (#8433)

2024-07-12 10:46:02 +03:00

test-grad0.cpp

ggml/examples: add backend support for numerical optimization (ggml/949)

2024-09-20 21:15:05 +03:00

test-grammar-integration.cpp

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

test-grammar-parser.cpp

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

test-json-schema-to-grammar.cpp

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

test-llama-grammar.cpp

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

test-log.cpp

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

test-lora-conversion-inference.sh

lora : fix llama conversion script with ROPE_FREQS (#9117)

2024-08-23 12:58:53 +02:00

test-model-load-cancel.cpp

…

test-opt.cpp

…

test-quantize-fns.cpp

ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)

2024-09-05 21:48:47 -04:00

test-quantize-perf.cpp

ggml : minor naming changes (#8433)

2024-07-12 10:46:02 +03:00

test-rope.cpp

Threadpool: take 2 (#8672)

2024-08-30 01:20:53 +02:00

test-sampling.cpp

sampling : avoid expensive softmax during greedy sampling (#9605)

2024-09-24 09:03:17 +03:00

test-tokenizer-0.cpp

llama : fix pre-tokenization of non-special added tokens (#8228)

2024-07-13 23:35:10 -04:00

test-tokenizer-0.py

py : logging and flake8 suppression refactoring (#7081)

2024-05-05 08:07:48 +03:00

test-tokenizer-0.sh

tests : fix test-tokenizer-0.sh

2024-05-28 15:04:09 +03:00

test-tokenizer-1-bpe.cpp

Detokenizer fixes (#8039)

2024-07-05 19:01:35 +02:00

test-tokenizer-1-spm.cpp

Detokenizer fixes (#8039)

2024-07-05 19:01:35 +02:00

test-tokenizer-random.py

llama : fix pre-tokenization of non-special added tokens (#8228)

2024-07-13 23:35:10 -04:00