Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 02:37:27 +02:00
Code Issues Packages Projects Releases Wiki Activity
10,793 Commits 759 Branches 7,321 Tags
master
Commit Graph
16 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Alberto Cabrera Pérez afc0e89698 sycl: refactor quantization to q8_1 (#14815) 
* sycl: quantization to q8_1 refactor

* Refactored src1 copy logic in op_mul_mat
 2025-07-28 11:05:53 +01:00
Alberto Cabrera Pérez cb4a63aad6 sycl: fixed semantics of block offset calculation (#14814) 2025-07-24 11:09:57 +01:00
Alberto Cabrera Pérez 725f23f1f3 sycl : backend documentation review (#13544) 
* sycl: reviewing and updating docs

* Updates Runtime error codes

* Improves OOM troubleshooting entry

* Added a llama 3 sample

* Updated supported models

* Updated releases table
 2025-05-19 14:38:20 +01:00
Alberto Cabrera Pérez f71f40a284 ci : upgraded oneAPI version in SYCL workflows and dockerfile (#13532) 2025-05-19 11:46:09 +01:00
Alberto Cabrera Pérezandromain.biessy 17512a94d6 sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs (#12858) 
* sycl : Implemented reorder Q4_0 mmvq

Signed-off-by: Alberto Cabrera <[email protected]>

* sycl : Fixed mmvq being called when reorder is disabled

* sycl : Improved comments in the quants header

Signed-off-by: Alberto Cabrera <[email protected]>

* Use static_assert

* safe_div -> ceil_div

* Clarify qi comment

* change the reorder tensor from init to execute OP

* dbg

* Undo changes to test-backend-ops

* Refactor changes on top of q4_0 reorder fix

* Missing Reverts

* Refactored opt_for_reorder logic to simplify code path

* Explicit inlining and unroll

* Renamed mul_mat_algo enum for consistency

---------

Signed-off-by: Alberto Cabrera <[email protected]>
Co-authored-by: romain.biessy <[email protected]>
 2025-05-09 16:34:08 +01:00
Alberto Cabrera Pérez 8733e0cf6e sycl: addressing non-contiguous src1 mul_mats (nc and batched) (#13343) 
* sycl: fixed non-contiguous src1 mul_mats (nc and batched)

* Fixed wrong static_cast inside kernel
 2025-05-08 10:08:01 +01:00
Alberto Cabrera Pérez 5a63980117 llama-bench: fixed size of fields to correctly map to values (#13183) 2025-04-29 17:24:36 +02:00
Alberto Cabrera Pérez 363f8c5d67 sycl : variable sg_size support for mmvq kernels (#12336) 2025-03-12 09:57:32 +00:00
Alberto Cabrera Pérez 0f77aae560 sycl : offload of get_rows set to 0 (#10432) 2024-11-29 20:38:45 +08:00
Alberto Cabrera Pérez 266b8519ee sycl : Reroute permuted mul_mats through oneMKL (#10408) 
This PR fixes the failing MUL_MAT tests for the sycl backend.
 2024-11-29 09:49:43 +00:00
Alberto Cabrera Pérez 557924f222 sycl: Revert MUL_MAT_OP support changes (#10385) 2024-11-19 08:50:04 +08:00
Alberto Cabrera Pérez 2e82ffa4af sycl : Fixes to broken builds and test-backend-ops (#10257) 
* Fixes broken build for the SYCL CUDA backend caused by non-explicit gemm call in outprod (merged in with RWKV6 in
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration #10133)

* Marks permuted MUL_MAT as unsupported to be able to run test-backend-ops

* Fixes asserts in norm to fix debug builds.
 2024-11-13 09:40:57 +00:00
Alberto Cabrera Pérez f536f4c439 [SYCL] Initial cmake support of SYCL for AMD GPUs (#9658) 
sycl: initial cmake support of SYCL for AMD GPUs
 2024-10-02 13:57:18 +01:00
Alberto Cabrera Pérez 51b6038636 sycl : update support conditions (#9394) 
* sycl : update support condition to im2col

Signed-off-by: Alberto Cabrera <[email protected]>

* Added TODO to remind supporting FP32 im2col

---------

Signed-off-by: Alberto Cabrera <[email protected]>
 2024-09-11 08:53:42 +08:00
Alberto Cabrera Pérez 5b0b8d8cfb sycl : Reenabled mmvq path for the SYCL Nvidia Backend (#8372) 
* SYCL : Reenabled mmvq path for the SYCL Nvidia Backend

* Reduced verbosity of comment
 2024-07-09 22:03:15 +08:00
Alberto Cabrera Pérez a130eccef4 labeler : updated sycl to match docs and code refactor (#8373) 2024-07-08 22:35:17 +02:00