mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

server : avoid checkpoint data host copies (#22558)

Browse Source 
* server : avoid checkpoint data host copies

* llama : refactor llama_io_read_i
This commit is contained in:
Georgi Gerganov
2026-05-02 18:03:25 +03:00
committed by GitHub
parent 09294365a9
commit 0754b7b6fe
6 changed files with 132 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+25 -28
View File
@@ -1900,14 +1900,14 @@ void llama_kv_cache::state_read(llama_io_read_i & io, llama_seq_id seq_id, llama
GGML_ASSERT(seq_id == -1 || (seq_id >= 0 && (size_t) seq_id < seq_to_stream.size()));
uint32_t n_stream_cur;
io.read_to(&n_stream_cur, sizeof(n_stream_cur));
io.read(&n_stream_cur, sizeof(n_stream_cur));
if (n_stream_cur != n_stream) {
throw std::runtime_error("n_stream mismatch");
}
for (uint32_t s = 0; s < n_stream; ++s) {
uint32_t cell_count;
io.read_to(&cell_count, sizeof(cell_count));
io.read(&cell_count, sizeof(cell_count));
if (cell_count == 0) {
continue;
@@ -2082,8 +2082,8 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
llama_pos pos;
uint32_t n_seq_id;
io.read_to(&pos, sizeof(pos));
io.read_to(&n_seq_id, sizeof(n_seq_id));
io.read(&pos, sizeof(pos));
io.read(&n_seq_id, sizeof(n_seq_id));
if (n_seq_id != 1) {
LLAMA_LOG_ERROR("%s: invalid seq_id-agnostic kv cell\n", __func__);
@@ -2092,7 +2092,7 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
if (hparams.n_pos_per_embd() > 1) {
llama_kv_cell_ext ext;
io.read_to(&ext, sizeof(ext));
io.read(&ext, sizeof(ext));
ubatch.pos[i + ubatch.n_tokens] = ext.y;
ubatch.pos[i + ubatch.n_tokens*2] = ext.x;
@@ -2101,7 +2101,7 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
// read the sequence id, but directly discard it - we will use dest_seq_id instead
{
llama_seq_id seq_id;
io.read_to(&seq_id, sizeof(seq_id));
io.read(&seq_id, sizeof(seq_id));
}
ubatch.pos[i] = pos;
@@ -2143,20 +2143,20 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
llama_pos pos;
uint32_t n_seq_id;
io.read_to(&pos, sizeof(pos));
io.read_to(&n_seq_id, sizeof(n_seq_id));
io.read(&pos, sizeof(pos));
io.read(&n_seq_id, sizeof(n_seq_id));
cells.pos_set(i, pos);
if (hparams.n_pos_per_embd() > 1) {
llama_kv_cell_ext ext;
io.read_to(&ext, sizeof(ext));
io.read(&ext, sizeof(ext));
cells.ext_set(i, ext);
}
for (uint32_t j = 0; j < n_seq_id; ++j) {
llama_seq_id seq_id;
io.read_to(&seq_id, sizeof(seq_id));
io.read(&seq_id, sizeof(seq_id));
if (seq_id < 0 || (uint32_t) seq_id >= n_seq_max) {
LLAMA_LOG_ERROR("%s: invalid seq_id, %d is out of range [0, %u)\n", __func__, seq_id, n_seq_max);
@@ -2189,8 +2189,8 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
uint32_t v_trans;
uint32_t n_layer;
io.read_to(&v_trans, sizeof(v_trans));
io.read_to(&n_layer, sizeof(n_layer));
io.read(&v_trans, sizeof(v_trans));
io.read(&n_layer, sizeof(n_layer));
if (n_layer != layers.size()) {
LLAMA_LOG_ERROR("%s: mismatched layer count (%u instead of %u)\n", __func__, n_layer, (uint32_t) layers.size());
@@ -2217,7 +2217,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read type of key
int32_t k_type_i_ref;
io.read_to(&k_type_i_ref, sizeof(k_type_i_ref));
io.read(&k_type_i_ref, sizeof(k_type_i_ref));
const int32_t k_type_i = (int32_t) k->type;
if (k_type_i != k_type_i_ref) {
LLAMA_LOG_ERROR("%s: mismatched key type (%d != %d, layer %d)\n", __func__, k_type_i, k_type_i_ref, il);
@@ -2226,7 +2226,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read row size of key
uint64_t k_size_row_ref;
io.read_to(&k_size_row_ref, sizeof(k_size_row_ref));
io.read(&k_size_row_ref, sizeof(k_size_row_ref));
const size_t k_size_row = ggml_row_size(k->type, n_embd_k_gqa);
if (k_size_row != k_size_row_ref) {
LLAMA_LOG_ERROR("%s: mismatched key row size (%zu != %zu, layer %d)\n", __func__, k_size_row, (size_t) k_size_row_ref, il);
@@ -2236,13 +2236,12 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
if (cell_count) {
if (sinfo.is_contiguous()) {
// Fast path: contiguous cells, single memcpy
ggml_backend_tensor_set(k, io.read(cell_count * k_size_row), sinfo.head() * k_size_row, cell_count * k_size_row);
io.read_tensor(k, sinfo.head() * k_size_row, cell_count * k_size_row);
} else {
// Slow path: scatter to non-contiguous positions
const void * src = io.read(cell_count * k_size_row);
for (uint32_t i = 0; i < cell_count; ++i) {
const size_t dst_offset = sinfo.idxs[0][i] * k_size_row;
ggml_backend_tensor_set(k, (const char*)src + i * k_size_row, dst_offset, k_size_row);
io.read_tensor(k, dst_offset, k_size_row);
}
}
}
@@ -2261,7 +2260,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read type of value
int32_t v_type_i_ref;
io.read_to(&v_type_i_ref, sizeof(v_type_i_ref));
io.read(&v_type_i_ref, sizeof(v_type_i_ref));
const int32_t v_type_i = (int32_t) v->type;
if (v_type_i != v_type_i_ref) {
LLAMA_LOG_ERROR("%s: mismatched value type (%d != %d, layer %d)\n", __func__, v_type_i, v_type_i_ref, il);
@@ -2270,7 +2269,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read row size of value
uint64_t v_size_row_ref;
io.read_to(&v_size_row_ref, sizeof(v_size_row_ref));
io.read(&v_size_row_ref, sizeof(v_size_row_ref));
const size_t v_size_row = ggml_row_size(v->type, n_embd_v_gqa);
if (v_size_row != v_size_row_ref) {
LLAMA_LOG_ERROR("%s: mismatched value row size (%zu != %zu, layer %d)\n", __func__, v_size_row, (size_t) v_size_row_ref, il);
@@ -2280,13 +2279,12 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
if (cell_count) {
if (sinfo.is_contiguous()) {
// Fast path: contiguous cells, single memcpy
ggml_backend_tensor_set(v, io.read(cell_count * v_size_row), sinfo.head() * v_size_row, cell_count * v_size_row);
io.read_tensor(v, sinfo.head() * v_size_row, cell_count * v_size_row);
} else {
// Slow path: scatter to non-contiguous positions
const void * src = io.read(cell_count * v_size_row);
for (uint32_t i = 0; i < cell_count; ++i) {
const size_t dst_offset = sinfo.idxs[0][i] * v_size_row;
ggml_backend_tensor_set(v, (const char*)src + i * v_size_row, dst_offset, v_size_row);
io.read_tensor(v, dst_offset, v_size_row);
}
}
}
@@ -2305,7 +2303,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read type of value
int32_t v_type_i_ref;
io.read_to(&v_type_i_ref, sizeof(v_type_i_ref));
io.read(&v_type_i_ref, sizeof(v_type_i_ref));
const int32_t v_type_i = (int32_t) v->type;
if (v_type_i != v_type_i_ref) {
LLAMA_LOG_ERROR("%s: mismatched value type (%d != %d, layer %d)\n", __func__, v_type_i, v_type_i_ref, il);
@@ -2314,7 +2312,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read element size of value
uint32_t v_size_el_ref;
io.read_to(&v_size_el_ref, sizeof(v_size_el_ref));
io.read(&v_size_el_ref, sizeof(v_size_el_ref));
const size_t v_size_el = ggml_type_size(v->type);
if (v_size_el != v_size_el_ref) {
LLAMA_LOG_ERROR("%s: mismatched value element size (%zu != %zu, layer %d)\n", __func__, v_size_el, (size_t) v_size_el_ref, il);
@@ -2323,7 +2321,7 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
// Read GQA embedding size
uint32_t n_embd_v_gqa_ref;
io.read_to(&n_embd_v_gqa_ref, sizeof(n_embd_v_gqa_ref));
io.read(&n_embd_v_gqa_ref, sizeof(n_embd_v_gqa_ref));
if (n_embd_v_gqa != n_embd_v_gqa_ref) {
LLAMA_LOG_ERROR("%s: mismatched GQA embedding size (%u != %u, layer %d)\n", __func__, n_embd_v_gqa, n_embd_v_gqa_ref, il);
return false;
@@ -2335,15 +2333,14 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
const uint32_t h = sinfo.head();
for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
const size_t dst_offset = (h + j * cells.size()) * v_size_el;
ggml_backend_tensor_set(v, io.read(cell_count * v_size_el), dst_offset, cell_count * v_size_el);
io.read_tensor(v, dst_offset, cell_count * v_size_el);
}
} else {
// Slow path: scatter to non-contiguous positions
for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
const void * src = io.read(cell_count * v_size_el);
for (uint32_t i = 0; i < cell_count; ++i) {
const size_t dst_offset = (sinfo.idxs[0][i] + j * cells.size()) * v_size_el;
ggml_backend_tensor_set(v, (const char*)src + i * v_size_el, dst_offset, v_size_el);
io.read_tensor(v, dst_offset, v_size_el);
}
}
}