mb8565 a7d35d51dc eval-callback : sum over the full tensor, not just the printed slice (#2019) ... ggml_print_tensor() accumulated `sum` inside the truncated print loop, which skips the middle of each row when ne[0] > 2*n (n = 3). The printed `sum =` therefore only covered the first n and last n elements per row, not the whole tensor. For example a {2688, 5} tensor reported the sum of 30 of its 13440 values. That makes the value useless for numerically comparing two runs, and it disagrees with mainline llama.cpp, whose eval-callback sums every element in a separate pass. This factors the per-element read into a small helper and computes the sum in its own loop over all elements (double accumulator). The truncated print is a separate, unchanged pass, so only the printed `sum =` value changes. The change is confined to examples/eval-callback. Co-authored-by: mb8565 <244351746+mb8565@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>		2026-06-24 08:57:19 +02:00
..
baby-llama	…
batched	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
batched-bench	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
batched.swift	…
benchmark	Quantization options (#1677)	2026-04-23 09:05:39 +02:00
convert-llama2c-to-ggml	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
cvector-generator	Fix DFlash oerformance with split mode graph (#1980)	2026-06-17 18:40:02 +02:00
deprecation-warning	…
embedding	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
eval-callback	eval-callback : sum over the full tensor, not just the printed slice (#2019)	2026-06-24 08:57:19 +02:00
export-lora	…
gbnf-validator	common : introduce composable PEG parser combinators for chat parsing and new jinja template engine (#1369)	2026-03-09 11:03:33 +01:00
gguf	…
gguf-hash	…
gguf-split	gguf-split: fix the split output files naming (#1336)	2026-03-02 08:43:47 +01:00
gritlm	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
imatrix	Fix DFlash oerformance with split mode graph (#1980)	2026-06-17 18:40:02 +02:00
infill	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
jeopardy	…
llama-bench	Add --defer-experts flag to defer expert mmap residency on Linux (#1634)	2026-04-16 08:54:44 +02:00
llama.android	…
llama.swiftui	…
llava	…
lookahead	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
lookup	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
main	common : introduce composable PEG parser combinators for chat parsing and new jinja template engine (#1369)	2026-03-09 11:03:33 +01:00
main-cmake-pkg	…
mtmd	Merge pull request #1893 from ikawrakow/ik/gemma4_mtmd_blindness	2026-06-16 07:47:37 +02:00
parallel	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
parser	Autoparser - complete refactoring of parser architecture (#1376)	2026-04-22 10:04:13 +02:00
passkey	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
perplexity	on-demand tensor reload (#1989)	2026-06-22 16:36:34 +02:00
quantize	Quantize: add extra output tensor for MTP (#1810)	2026-05-17 13:59:56 +03:00
quantize-stats	Update autofix and presets (#1867)	2026-05-24 07:30:44 +03:00
retrieval	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
rpc	Refactor chat and server file (#1062)	2025-12-15 08:27:20 +01:00
save-load-state	server: enable checkpoint for recurrent models (#1310)	2026-02-26 06:51:18 +01:00
server	server: variance based checkpoint eviction (#2020)	2026-06-24 08:54:07 +02:00
simple	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
speculative	Fix two speculative-decoding crashes that prevent any usage (#1760)	2026-05-09 08:36:38 +03:00
sweep-bench	Cleaner log for adjusted splits (#1494)	2026-03-24 07:49:40 +01:00
sycl	…
tokenize	spec : add self speculative decoding, ngram and refactor (#1261)	2026-02-13 19:04:55 +01:00
CMakeLists.txt	Port mdmd from mainline + Qwen2/2.5-VL support (#798)	2025-09-27 08:45:29 +02:00
Miku.sh	…
base-translate.sh	…
chat-13B.bat	…
chat-13B.sh	…
chat-persistent.sh	…
chat-vicuna.sh	…
chat.sh	…
convert_legacy_llama.py	…
json_schema_pydantic_example.py	…
json_schema_to_grammar.py	Autoparser - complete refactoring of parser architecture (#1376)	2026-04-22 10:04:13 +02:00
llama.vim	…
llm.vim	…
pydantic_models_to_grammar.py	…
pydantic_models_to_grammar_examples.py	…
reason-act.sh	…
regex_to_grammar.py	…
server-llama2-13B.sh	…
server_embd.py	…
ts-type-to-grammar.sh	…