CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
5,962 Commits 498 Branches 4,731 Tags
fc692ed4989c7acb3fb2d57bd26c16f87593a9fc
Commit Graph

5962 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aaron Teo
fc692ed498 ggml-zdnn: figure out why sigtrap is happening 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 18:00:28 +08:00
Aaron Teo
08de84ef85 ggml-zdnn: bugfix transform ztensor vs origtensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:57:57 +08:00
Aaron Teo
032dce5a6a ggml-zdnn: fix sequencing of transforms 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:46:17 +08:00
Aaron Teo
cf0e190c40 ggml-zdnn: add more safeguards in matmul 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:44:39 +08:00
Aaron Teo
f239bbb02d ggml-zdnn: move weights transform into mulmat 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:38:44 +08:00
Aaron Teo
092fa3a328 ggml-zdnn: activate bias transform in matmul 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:27:35 +08:00
Aaron Teo
f7e8d6f2b2 ggml-zdnn: add logger to check if mat mul ops go through set_tensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:17:12 +08:00
Aaron Teo
6d71749c26 ggml-zdnn: add more debug info for extra buffer transform 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:10:07 +08:00
Aaron Teo
4b2f1cb1b8 ggml-zdnn: add bias data transform 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 16:05:53 +08:00
Aaron Teo
f800c80281 ggml-zdnn: add bias ztensor and data free 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 15:59:52 +08:00
Aaron Teo
bee7dd3020 ggml-zdnn: tighten memory usage, change string allocation 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 15:55:42 +08:00
Aaron Teo
aef93b3908 ggml-zdnn: add bias init_tensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-28 15:41:56 +08:00
Aaron Teo
f263f5d9ae ggml-zdnn: fix missing data transform call 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 18:30:10 +08:00
Aaron Teo
1c75ed63e5 ggml-zdnn: fix compiler error missing type 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 18:22:34 +08:00
Aaron Teo
a1d8568c14 ggml-zdnn: impl matmul 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 18:13:07 +08:00
Aaron Teo
59e9805ab0 ggml-zdnn: code clean up 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 16:26:29 +08:00
Aaron Teo
c1653ab639 ggml-zdnn: fix incorrect ztensor shape, reduce memory padding 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 16:22:06 +08:00
Aaron Teo
828519659b ggml-zdnn: update supports_op matmul matrix 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 16:11:37 +08:00
Aaron Teo
18658b8607 ggml-zdnn: impl init_tensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 12:02:20 +08:00
Aaron Teo
da2e0e70ba ggml-zdnn: switch buffers back and set to arbitrary number 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 02:31:22 +08:00
Aaron Teo
63fbc45ed6 ggml-zdnn: switch to std vector instead of array 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 01:09:01 +08:00
Aaron Teo
b7f4b6fde3 ggml-zdnn: rework init_tensor to create new buffers 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 01:03:53 +08:00
Aaron Teo
ee0ed78d54 ggml-zdnn: add check for view tensors to prevent init_tensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:56:32 +08:00
Aaron Teo
13c64448bd ggml-zdnn: assign tensor->extra to buffer 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:48:32 +08:00
Aaron Teo
13c05872f2 ggml-zdnn: implement at least 1 op to test 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:44:05 +08:00
Aaron Teo
9e84742e72 ggml-zdnn: test ztensor finding in init_tensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:40:22 +08:00
Aaron Teo
af9f4f0039 ggml-zdnn: fix compiler warnings and bugfixes 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:25:41 +08:00
Aaron Teo
ae2f656d7e ggml-zdnn: bugfix new impl 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:18:53 +08:00
Aaron Teo
7c6395f826 ggml-zdnn: rewrite the backend implementation 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-24 00:14:45 +08:00
Aaron Teo
04ddb2ac95 ggml-zdnn: update op out_prod to use tensor->extra 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-23 19:51:37 +08:00
Aaron Teo
77a753297b ggml-zdnn: support op out_prod 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-23 19:28:51 +08:00
Aaron Teo
11d58d29de ggml-zdnn: add comments to prevent accidentally deleting lines 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-23 14:54:44 +08:00
Aaron Teo
529bdb9fbd ggml-zdnn: last working matmul version 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-22 00:29:47 +08:00
Aaron Teo
60b9874dea ggml-zdnn: update set_tensor logging to check only for matmul 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-21 21:11:39 +08:00
Aaron Teo
b9756b6dd4 ggml-zdnn: add more loggers 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-21 21:09:21 +08:00
Aaron Teo
1989fc9bf4 ggml-zdnn: add set_tensor 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-21 20:37:53 +08:00
Aaron Teo
36d76c30fb ggml-zdnn: run compute and store into tensor->extra 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-21 20:30:54 +08:00
Aaron Teo
02cfcfb270 ggml-zdnn: add output buffer check 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-21 20:19:20 +08:00
Aaron Teo
fd4914b060 ggml-zdnn: tensor->extra logging check 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: add layout name mapping, ztensor information

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: separate logging into its own line

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: add shape comparison

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: add ggml_tensor shape log

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: fix incorrect shape logging

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-18 21:00:30 +08:00
Aaron Teo
e084821a3f ggml-zdnn: inital backend impl 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: temp change z17 to arch15

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: fix build bugs

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-07-18 20:04:20 +08:00
Georgi Gerganov
01612b7409 llama : reuse compute graphs (#14482) 
* llama : reuse compute graphs

ggml-ci

* llama-bench : add graph reuse parameter

ggml-ci

* cont : remove the parameter and the sched resets

ggml-ci

* graph : rename update() to can_reuse()

ggml-ci

* params : remove is_same()

ggml-ci

* graph : set res->params in llm_graph_context constructor

ggml-ci

* graph : avoid set_max_nodes in llm_graph_result

ggml-ci

* kv-cache : reuse llama_context's graph result instance

ggml-ci

* context : reset the previous graph result upon memory updates

ggml-ci

* batch : llama_ubatch now carries its data instead of pointing to balloc

ggml-ci

* merge : fix build

ggml-ci

* graph : fix can_reuse() checks when flash-attention is disabled

* graph : move llm_graph_result impl in source file + debug env

ggml-ci
b5922 		2025-07-17 19:08:33 +03:00
Tarek Dakhran
086cf81e88 llama : fix parallel processing for lfm2 (#14705) b5921 2025-07-17 09:22:11 +02:00
Georgi Gerganov
d9b691081c kv-cache : opt mask set input (#14600) 
ggml-ci
b5920 		2025-07-17 09:49:15 +03:00
Georgi Gerganov
ad57d3edd2 batch : fix uninitialized has_cpl flag (#14733) 
ggml-ci
b5919 		2025-07-17 09:45:54 +03:00
Sigbjørn Skjæret
1ba45d4982 ci : disable failing vulkan crossbuilds (#14723) 2025-07-16 20:52:08 -03:00
Sigbjørn Skjæret
19e5943d9e convert : make hf token optional (#14717) 
* make hf token optional

* fail if we can't get necessary tokenizer config
 2025-07-16 23:17:43 +02:00
Diner Burger
496957e1cb llama : fix parameter order for hybrid memory initialization (#14725) b5916 2025-07-16 21:17:25 +02:00
Reese Levine
21c021745d ggml: Add initial WebGPU backend (#14521) 
* Minimal setup of webgpu backend with dawn. Just prints out the adapter and segfaults

* Initialize webgpu device

* Making progress on setting up the backend

* Finish more boilerplate/utility functions

* Organize file and work on alloc buffer

* Add webgpu_context to prepare for actually running some shaders

* Work on memset and add shader loading

* Work on memset polyfill

* Implement set_tensor as webgpu WriteBuffer, remove host_buffer stubs since webgpu doesn't support it

* Implement get_tensor and buffer_clear

* Finish rest of setup

* Start work on compute graph

* Basic mat mul working

* Work on emscripten build

* Basic WebGPU backend instructions

* Use EMSCRIPTEN flag

* Work on passing ci, implement 4d tensor multiplication

* Pass thread safety test

* Implement permuting for mul_mat and cpy

* minor cleanups

* Address feedback

* Remove division by type size in cpy op

* Fix formatting and add github action workflows for vulkan and metal (m-series) webgpu backends

* Fix name

* Fix macos dawn prefix path
b5915 		2025-07-16 18:18:51 +03:00
tempstudio
b0f0ecc3dc model : support output bias for qwen2 (#14711) 
Co-authored-by: qwaqrm <qwaqrm@126.com>
b5914 		2025-07-16 18:02:06 +03:00
Georgi Gerganov
225e7a1438 llama : add high-throughput mode (#14363) 
* kv-cache : prepare K/V buffers for separation

ggml-ci

* batched-bench : fix oob write

ggml-ci

* llama : add "virtual sequences"

ggml-ci

* llama : use "stream" vs "virtual sequence"

ggml-ci

* graph : fix stream splitting when KV cache is not used

ggml-ci

* kv-cache : add multi-stream save/load support

ggml-ci

* llama : add "--attn-streams" flag

ggml-ci

* kv-cache : fix handling when find_slot fails

ggml-ci

* kv-cache : restore find_slot impl

ggml-ci

* kv-cache : add comments

* kv-cache : add bounds checks for sequence id

ggml-ci

* cont : add n_seq_max to batch allocr

ggml-ci

* kv-cache : perform stream copies lazily after llama_synchronize

ggml-ci

* kv-cache : avoid throwing exceptions across the C boundary

ggml-ci

* CUDA: 4D FlashAttention support (#14628)

* CUDA: 4D FlashAttention support

* CUDA: fix WMMA FA kernel

* llama : rename attn_streams -> kv_unified

ggml-ci

* common : rename kv_split -> kv_unified

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
b5913 		2025-07-16 16:35:42 +03:00