Commit Graph

9 Commits (c3bfc9bfdab115c9654ccc62ab708a78ac293664)

Author SHA1 Message Date
Neo Zhang Jianyu c3bfc9bfda
Support multiple GPUs (split mode) on SYCL backend (llama/5806)
* suport multiple cards: split-mode - layer|row

* rm warning

* rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test

* update news

* fix merge error

* update according to review comments
2024-03-08 11:38:32 +02:00
AidanBeltonS 11dd0d4482
Use batched mul_mat pathway (llama/5591)
* Use batched mul_mat pathway

* rm extra line

* Explicitly state scaled data type

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-03-08 11:38:31 +02:00
AidanBeltonS 8408a4be8e
Add support for soft_max ALiBi (llama/5639)
* Add support for bias

* Update pre-processor

* rm commented code

* fix format

* fix CI

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-02-28 13:00:29 +02:00
Georgi Gerganov fac5b43830
code : normalize enum names (llama/5697)
* coda : normalize enum names

ggml-ci

* code : cont

* code : cont
2024-02-25 19:58:46 +02:00
UEXTM.com 1cb64f7368
Introduce backend GUIDs (ggml/743)
* Introduce backend GUIDs

Initial proposed implementation of backend GUIDs
(Discussed in https://github.com/ggerganov/ggml/pull/741)

Hardcoded CPU backend GUID (for now)
Change ggml_backend_is_cpu logic to use GUID

* Remove redundant functions

Remove redundant functions `ggml_backend_i::get_name` and `ggml_backend_guid` which are not desired for future expansion

* Add spaces to match style

Co-authored-by: slaren <slarengh@gmail.com>

* Fix brace style to match

Co-authored-by: slaren <slarengh@gmail.com>

* Add void to () in function signature

Co-authored-by: slaren <slarengh@gmail.com>

* Add back ggml_backend_guid and make CPU_GUID a local static in ggml_backend_cpu_guid

* add guids to all backends

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-02-25 19:58:45 +02:00
Meng, Hengyu 208de95ac7
conext add name (llama/5624)
* [SYCL] conext add name

* name should start with SYCL*
2024-02-22 15:12:36 +02:00
AidanBeltonS c2ce39c795
Update ggml_sycl_op_mul_mat_vec_q (llama/5502)
* Update ggml_sycl_op_mul_mat_vec_q

* Apply suggestions from code review

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

* revert suggestion on macro

* fix bug

* Add quant type GGML_TYPE_IQ1_S to unsupported

* fix format

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-02-22 15:12:36 +02:00
Abhilash Majumder 462ffc58db
ggml-sycl: Replace 3d ops with macro (llama/5458)
* use macro

* use macro

* fix format
2024-02-19 15:53:21 +02:00
Georgi Gerganov 8b17a2f776
src : relocate new backend sources 2024-02-10 09:55:47 +02:00