Skip to content
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

Jump to bottom

b3181 #170

Merged
merged 8 commits into from
Jun 18, 2024
Merged

b3181 #170

merged 8 commits into from
Jun 18, 2024

Conversation

Nexesenex
Copy link
Owner

ggerganov and others added 8 commits June 18, 2024 09:50
@ggerganov @slaren
whisper : use ggml_backend_sched (whisper/2239)
e6ecc2b 
* whisper : use ggml_backend_sched (wip)

* use sched in whisper_allocr

* whisper : single backend in whisper_context

* whisper : remove whisper_state->backends_used

* whisper : remove whisper_context->backend

* whisper : reset scheduler after init

* whisper : fix external encoder (e.g. CoreML)

* whisper : cleanup

* whisper : handle null GPU buffer types + fix sycl

---------

Co-authored-by: slaren <[email protected]>
@ggerganov
ggml : sync
5326bcc
@abgulati
readme : update UI list (#7943)
1193778
@thxCode
chore: clean useless beam search param (#7985)
b96f9af 
Signed-off-by: thxCode <[email protected]>
@drepper
Allow compiling with CUDA without CUDA runtime installed (#7989)
6166527 
On hosts which are not prepared/dedicated to execute code using CUDA
it is still possible to compile llama.cpp with CUDA support by just
installing the development packages.  Missing are the runtime
libraries like /usr/lib64/libcuda.so* and currently the link step
will fail.

The development environment is prepared for such situations.  There
are stub libraries for all the CUDA libraries available in the
$(CUDA_PATH)/lib64/stubs directory.  Adding this directory to the end
of the search path will not change anything for environments which
currently work fine but will enable compiling llama.cpp also in case
the runtime code is not available.
@jojorne
Fix no gcc pragma on Windows (#7751)
84f6de1
@CISC
Only use FIM middle token if it exists (#7648)
91c188d 
* Only use FIM middle if it exists

* Only use FIM middle if it exists
@jaime-m-p
tokenizer : BPE fixes (#7530)
37bef89 
* Random test: add_bos_token, add_eos_token
* Random test: add BPE models for testing
* Custom regex split fails with codepoint 0
* Fix falcon punctuation regex
* Refactor llm_tokenizer_bpe: move code to constructor
* Move 'add_special_bos/eos' logic to llm_tokenizer_bpe
* Move tokenizer flags to vocab structure.
* Default values for special_add_bos/eos
* Build vocab.special_tokens_cache using vocab token types
* Generalize 'jina-v2' per token attributes
* Fix unicode whitespaces (deepseek-coder, deepseek-llm)
* Skip missing byte tokens (falcon)
* Better unicode data generation
* Replace char32_t with uint32_t
@Nexesenex Nexesenex merged commit 0136b3f into Nexesenex:skystream Jun 18, 2024
37 of 40 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
examples ggml python script server testing
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
8 participants
@Nexesenex @ggerganov @abgulati @thxCode @drepper @jojorne @CISC @jaime-m-p