wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

server : disable on-device spec checkpoints (#24108)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-04 19:30:59 +03:00
committed by GitHub
parent 260862b8ca
commit 7c158fbb4a
2 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+6 -6
View File
@@ -2512,7 +2512,7 @@ private:
llama_memory_seq_pos_max(llama_get_memory(ctx_tgt), slot.id));
if (use_ckpt_dft) {
slot.spec_ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
slot.spec_ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
}
slot.spec_prompt = slot.prompt.tokens.get_text_tokens();
@@ -2551,7 +2551,7 @@ private:
if (ctx_dft) {
if (use_ckpt_dft) {
ckpt.load_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.load_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
}
common_context_seq_rm(ctx_dft.get(), slot.id, ckpt.pos_max + 1, -1);
@@ -2568,7 +2568,7 @@ private:
if (use_ckpt_tgt) {
//const int64_t t_start = ggml_time_us();
ckpt.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
//const int64_t t_total = ggml_time_us() - t_start;
//printf("checkpoint total: %f ms\n", t_total / 1000.0);
@@ -2580,7 +2580,7 @@ private:
}
if (use_ckpt_dft) {
ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
}
}
}
@@ -3447,13 +3447,13 @@ private:
SLT_DBG(slot, "restoring speculative checkpoint (pos_min = %d, pos_max = %d, size = %zu)\n", ckpt.pos_min, ckpt.pos_max, ckpt.size());
{
ckpt.load_tgt(slot.ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.load_tgt(slot.ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
common_context_seq_rm(slot.ctx_tgt, slot.id, ckpt.pos_max + 1, -1);
}
if (slot.ctx_dft) {
ckpt.load_dft(slot.ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.load_dft(slot.ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
common_context_seq_rm(slot.ctx_dft, slot.id, ckpt.pos_max + 1, -1);
}