Skip to content

[SYCL] fix mul_mat fault in CI/unit-test #5862

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 38 commits into from
Mar 5, 2024
Merged

[SYCL] fix mul_mat fault in CI/unit-test #5862

Changes from 5 commits
Commits
Show all changes
38 commits
Select commit Hold shift + click to select a range
99b9eda
fix mul_mat fault in cpy_f32_f16
NeoZhangJianyu Mar 3, 2024
ddc1249
rm unused function
NeoZhangJianyu Mar 4, 2024
0dce40a
add wait() for memcpy
LiangtaoJin Mar 4, 2024
89524c2
restore ci/run.sh, rename struct defination, fix bug in ggml_sycl_op_…
NeoZhangJianyu Mar 5, 2024
32bf3df
fix format issue
NeoZhangJianyu Mar 5, 2024
8899bdb
llama : fix segfault from unknown model arch name (#5820)
compilade Mar 2, 2024
9758243
llama : refactor internal quantization functions (#5830)
ngxson Mar 2, 2024
dcf09d3
scripts : add pod-llama.sh
ggerganov Mar 2, 2024
d0c9a89
ggml : IQ3_S improvements (#5829)
ikawrakow Mar 2, 2024
9285e71
convert-hf : make model class definitions self-contained (#5825)
cebtenzzre Mar 2, 2024
0867b91
convert : automatically fall back to HfVocab if tokenizer.model doesn…
cebtenzzre Mar 2, 2024
1a5ed7a
ggml : fix IQ3_S AVX implementation (#5834)
ggerganov Mar 2, 2024
506177d
llama : add abort_callback to interrupt computation (#5409)
Xarbirus Mar 2, 2024
8479e7d
server: tests: passkey challenge / self-extend with context shift de…
phymbert Mar 2, 2024
756a4ac
flake.lock: Update (#5842)
ggerganov Mar 3, 2024
f72df31
server : init http requests thread pool with --parallel if set (#5836)
phymbert Mar 3, 2024
23a6275
ci : schedule slow server tests only on Release or on demand (#5839)
phymbert Mar 3, 2024
524864d
llama : fix llama_copy_state_data with fragmented KV cache (#5840)
compilade Mar 3, 2024
8bb872d
gguf-dump : support i-quants (#5841)
Nindaleth Mar 3, 2024
e55ee8a
llama : allow for user specified embedding pooling type (#5849)
iamlemec Mar 3, 2024
fd4a186
readme : add API changes section
ggerganov Mar 3, 2024
22dd02a
cuda : fix data race in soft max (#5853)
slaren Mar 3, 2024
f3a6dd6
main : support special tokens as reverse/anti prompt (#5847)
dranger003 Mar 4, 2024
edabfad
common : use LLAMA_DEFAULT_SEED (#5855)
dranger003 Mar 4, 2024
9e4d115
add some new ops, fix some operators and add batch operations to cert…
leejet Mar 3, 2024
b15e753
sync : ggml
ggerganov Mar 4, 2024
3ae5525
add alias for chat template (#5858)
ngxson Mar 4, 2024
e245d6c
speculative : implement stochastic speculative sampling (#5625)
mscheong01 Mar 4, 2024
465e411
cmake : handle cases where git index is not found in .git (#5844)
danemadsen Mar 4, 2024
d87093e
ggml : introduce ggml_status (ggml/750)
Xarbirus Mar 4, 2024
3a44f13
sync : ggml
ggerganov Mar 4, 2024
86e4a3b
ggml : fix unknown status (#0)
ggerganov Mar 4, 2024
dabfd53
flake : fix
ggerganov Mar 4, 2024
2e4e9c0
llama : fix embeddings (#5796)
ggerganov Mar 4, 2024
6aac3d4
nix: static build (#5814)
hutli Mar 5, 2024
49a8477
fix speculative decoding build on windows (#5874)
jquesnelle Mar 5, 2024
96b9179
rebase and rm tailing space
NeoZhangJianyu Mar 5, 2024
fa30cc8
Merge branch 'master' into fix_mul_mat
NeoZhangJianyu Mar 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading