vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rewrite history to fix bad vulkan shader commits without increasing repo size

Browse source 
added dpe colab (+8 squashed commit)

Squashed commit:

[b8362da4] updated lite

[ed6c037d] move nsigma into the regular sampler stack

[ac5f61c6] relative filepath fixed

[05fe96ab] export template

[ed0a5a3e] nix_example.md: refactor (#1401)

* nix_example.md: add override example

* nix_example.md: drop graphics example, already basic nixos knowledge

* nix_example.md: format

* nix_example.md: Vulkan is disabled on macOS

Disabled in: 1ccd253acc

* nix_examples.md: nixpkgs.config.cuda{Arches -> Capabilities}

Fixes: https://github.com/LostRuins/koboldcpp/issues/1367

[675c62f7] AutoGuess: Phi 4 (mini) (#1402)

[4bf56982] phrasing

[b8c0df04] Add Rep Pen to Top N Sigma sampler chain (#1397)

- place after nsigma and before xtc (+3 squashed commit)

Squashed commit:

[87c52b97] disable VMM from HIP

[ee8906f3] edit description

[e85c0e69] Remove Unnecessary Rep Counting (#1394)

* stop counting reps

* fix range-based initializer

* strike that - reverse it
This commit is contained in:
Concedo 2025-03-05 00:02:20 +08:00
parent 50eae1ffeb
commit 6b7d2349a7
114 changed files with 6666 additions and 2642 deletions
Download patch file Download diff file Expand all files Collapse all files

17
ggml/src/ggml-backend.cpp
View file

@ -126,11 +126,12 @@ void * ggml_backend_buffer_get_base(ggml_backend_buffer_t buffer) {
return base;
}
void ggml_backend_buffer_init_tensor(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor) {
enum ggml_status ggml_backend_buffer_init_tensor(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor) {
// init_tensor is optional
if (buffer->iface.init_tensor) {
buffer->iface.init_tensor(buffer, tensor);
return buffer->iface.init_tensor(buffer, tensor);
}
return GGML_STATUS_SUCCESS;
}
void ggml_backend_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value) {
@ -1647,7 +1648,7 @@ ggml_backend_t ggml_backend_sched_get_tensor_backend(ggml_backend_sched_t sched,
// utils
void ggml_backend_view_init(struct ggml_tensor * tensor) {
enum ggml_status ggml_backend_view_init(struct ggml_tensor * tensor) {
GGML_ASSERT(tensor->buffer == NULL);
GGML_ASSERT(tensor->view_src != NULL);
GGML_ASSERT(tensor->view_src->buffer != NULL);
@ -1655,10 +1656,10 @@ void ggml_backend_view_init(struct ggml_tensor * tensor) {
tensor->buffer = tensor->view_src->buffer;
tensor->data = (char *)tensor->view_src->data + tensor->view_offs;
ggml_backend_buffer_init_tensor(tensor->buffer, tensor);
return ggml_backend_buffer_init_tensor(tensor->buffer, tensor);
}
void ggml_backend_tensor_alloc(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor, void * addr) {
enum ggml_status ggml_backend_tensor_alloc(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor, void * addr) {
GGML_ASSERT(tensor->buffer == NULL);
GGML_ASSERT(tensor->data == NULL);
GGML_ASSERT(tensor->view_src == NULL);
@ -1668,7 +1669,7 @@ void ggml_backend_tensor_alloc(ggml_backend_buffer_t buffer, struct ggml_tensor
tensor->buffer = buffer;
tensor->data = addr;
ggml_backend_buffer_init_tensor(buffer, tensor);
return ggml_backend_buffer_init_tensor(buffer, tensor);
}
static struct ggml_tensor * graph_copy_dup_tensor(struct ggml_hash_set hash_set, struct ggml_tensor ** node_copies,
@ -1714,7 +1715,8 @@ static void graph_copy_init_tensor(struct ggml_hash_set * hash_set, struct ggml_
struct ggml_tensor * dst = node_copies[id];
if (dst->view_src != NULL) {
graph_copy_init_tensor(hash_set, node_copies, node_init, src->view_src);
ggml_backend_view_init(dst);
enum ggml_status status = ggml_backend_view_init(dst);
GGML_ASSERT(status == GGML_STATUS_SUCCESS);
}
else {
ggml_backend_tensor_copy(src, dst);
@ -1829,7 +1831,6 @@ bool ggml_backend_compare_graph_backend(ggml_backend_t backend1, ggml_backend_t
assert(g1->n_nodes == g2->n_nodes);
for (int i = 0; i < g1->n_nodes; i++) {
//printf("eval %d/%d\n", i, g1->n_nodes);
struct ggml_tensor * t1 = g1->nodes[i];
struct ggml_tensor * t2 = g2->nodes[i];