nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

chore : correct typos [no ci] (#20041)

Browse Source 
* fix(docs): correct typos found during code review

Non-functional changes only:
- Fixed minor spelling mistakes in comments
- Corrected typos in user-facing strings
- No variables, logic, or functional code was modified.

Signed-off-by: Marcel Petrick <mail@marcelpetrick.it>

* Update docs/backend/CANN.md

Co-authored-by: Aaron Teo <taronaeo@gmail.com>

* Revert "Auxiliary commit to revert individual files from 846d1c301281178efbc6ce6060ad34c1ebe45af8"

This reverts commit 02fcf0c7db661d5ff3eff96b2b2db9fdb7213256.

* Update tests/test-backend-ops.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update tests/test-backend-ops.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Signed-off-by: Marcel Petrick <mail@marcelpetrick.it>
Co-authored-by: Aaron Teo <taronaeo@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Marcel Petrick
2026-03-05 08:50:21 +01:00
committed by GitHub
co-authored by Aaron Teo Sigbjørn Skjæret
parent 7a99dc85e2
commit 92f7da00b4
81 changed files with 160 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/ggml-opencl.cpp
+5 -5
View File
@@ -313,7 +313,7 @@ struct ProfilingInfo {
cl_ulong cmd_duration_ns;
// The time for the kernel to complete - COMPLETE - END
cl_ulong cmd_complete_duration_ns;
// Total time to finish the kernel - COMPELTE - QUEUED
// Total time to finish the kernel - COMPLETE - QUEUED
cl_ulong cmd_total_duration_ns;
// Global and local work sizes.
size_t global_size[3];
@@ -2555,7 +2555,7 @@ static std::vector<ggml_backend_device> ggml_opencl_probe_devices(ggml_backend_r
cl_platform_id platform_ids[NPLAT];
if (clGetPlatformIDs(NPLAT, platform_ids, &n_platforms) != CL_SUCCESS) {
GGML_LOG_ERROR("ggml_opencl: plaform IDs not available.\n");
GGML_LOG_ERROR("ggml_opencl: platform IDs not available.\n");
return found_devices;
}
@@ -3339,7 +3339,7 @@ static void ggml_backend_opencl_synchronize(ggml_backend_t backend) {
CL_CHECK(clReleaseEvent(evt));
}
// Syncronizes the 'backend_ctx's device with others so that commands
// Synchronizes the 'backend_ctx's device with others so that commands
// enqueued to it won't start until commands in the other devices have
// completed.
static void sync_with_other_backends(ggml_backend_opencl_context * backend_ctx) {
@@ -3997,7 +3997,7 @@ struct ggml_backend_opencl_buffer_context {
// The buffer_context is initially created by ggml_backend_buft_alloc_buffer
// before any tensor is initialized (at the beginning of alloc_tensor_range).
// Hence, there is alway a buffer object in this vector. When each tensor is
// Hence, there is always a buffer object in this vector. When each tensor is
// being initialized, this original buffer object will be released if both
// flattening and small allocation are enabled, and additional buffer
// objects will be created in init_tensor to represent flattened quantized
@@ -4132,7 +4132,7 @@ static void ggml_backend_opencl_buffer_set_tensor(ggml_backend_buffer_t buffer,
//GGML_ASSERT(offset == 0);
// We create subbuffers from the original tensor buffer for scales and
// quants - i.e., scales and quants are aliases into the buffer obejct
// quants - i.e., scales and quants are aliases into the buffer object
// that backs the original tensor. This is a cleaner way to adapt to the
// new memory management.
// In the old code, we allocate new buffers for scales and quants