slaren 0d56246f4b

ggml : group all experts in a single ggml_mul_mat_id (#6505) ...

* ggml : group all experts in a single ggml_mul_mat_id
cuda : improve mmid row copy

* cuda : fix bin bcast with non-cont src0

* test-backend-ops : only run all mul mat tests for base types

* llama : disable moe offloading with SYCL

---------

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

2024-04-18 15:18:48 +02:00

..

build-info.cmake

cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)

2023-11-27 21:25:42 +02:00

build-info.sh

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

check-requirements.sh

python : add check-requirements.sh and GitHub workflow (#4585)

2023-12-29 16:50:29 +02:00

ci-run.sh

ci : add model tests + script wrapper (#4586)

2024-01-26 14:18:00 +02:00

compare-commits.sh

ggml : group all experts in a single ggml_mul_mat_id (#6505)

2024-04-18 15:18:48 +02:00

compare-llama-bench.py

compare-llama-bench.py: fix long hexsha args (#6424)

2024-04-01 13:30:43 +02:00

convert-gg.sh

scripts : helper convert script

2023-08-27 15:24:58 +03:00

gen-authors.sh

license : update copyright notice + add AUTHORS (#6405)

2024-04-09 09:23:19 +03:00

gen-build-info-cpp.cmake

cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)

2023-11-27 21:25:42 +02:00

get-flags.mk

build : pass all warning flags to nvcc via -Xcompiler (#5570)

2024-02-18 16:21:52 -05:00

get-hellaswag.sh

scripts : add get-winogrande.sh

2024-01-18 20:45:39 +02:00

get-pg.sh

scripts : improve get-pg.sh (#4838)

2024-01-09 19:21:13 +02:00

get-wikitext-2.sh

model: support arch DbrxForCausalLM (#6515)

2024-04-13 11:33:52 +02:00

get-wikitext-103.sh

lookup: complement data from context with general text statistics (#5479)

2024-03-23 01:24:36 +01:00

get-winogrande.sh

scripts : add get-winogrande.sh

2024-01-18 20:45:39 +02:00

hf.sh

scripts : add --outdir option to hf.sh (#6600)

2024-04-11 16:22:47 +03:00

install-oneapi.bat

support SYCL backend windows build (#5208)

2024-01-31 08:08:07 +05:30

LlamaConfig.cmake.in

cuda : rename build flag to LLAMA_CUDA (#6299)

2024-03-26 01:16:01 +01:00

pod-llama.sh

cuda : rename build flag to LLAMA_CUDA (#6299)

2024-03-26 01:16:01 +01:00

qnt-all.sh

scripts : add pipefail

2023-08-29 10:50:30 +03:00

run-all-perf.sh

scripts : add pipefail

2023-08-29 10:50:30 +03:00

run-all-ppl.sh

scripts : add pipefail

2023-08-29 10:50:30 +03:00

run-with-preset.py

scripts : move run-with-preset.py from root to scripts folder

2024-01-26 17:09:44 +02:00

server-llm.sh

cuda : rename build flag to LLAMA_CUDA (#6299)

2024-03-26 01:16:01 +01:00

sync-ggml-am.sh

license : update copyright notice + add AUTHORS (#6405)

2024-04-09 09:23:19 +03:00

sync-ggml.last

sync : ggml

2024-04-09 20:29:06 +03:00

sync-ggml.sh

license : update copyright notice + add AUTHORS (#6405)

2024-04-09 09:23:19 +03:00

verify-checksum-models.py

scripts : use /usr/bin/env in shebang (#3313)

2023-09-22 23:52:23 -04:00