server: refactor, add server_slot_sched, prompt running hash (#32154)

* server: refactor, add server_slot_sched, prompt running hash

* use sha256 hash
This commit is contained in:
Xuan-Son Nguyen authored and GitHub committed 2026-11-15 09:37:17 +01:00
1 parent 58a4a6b49c
commit 429460dc0e
11 files changed
+790 -474

No files matched your search

-223
View File
@@ -1729,226 +1729,3 @@ json server_task_result_get_lora::to_json() {
json server_task_result_apply_lora::to_json() {
return json {{ "success", true }};
}
//
// server_prompt_cache
//
size_t server_prompt_cache::size() const {
size_t res = 0;
for (const auto & state : states) {
res += state.size();
}
return res;
}
size_t server_prompt_cache::n_tokens() const {
size_t res = 0;
for (const auto & state : states) {
res += state.prompt.n_tokens();
}
return res;
}
server_prompt_cache_state * server_prompt_cache::alloc(const server_prompt & prompt, size_t state_size_tgt, size_t state_size_dft) {
// first check if the current state is contained fully in the cache
for (auto it = states.begin(); it != states.end(); ++it) {
const int cur_lcp_len = it->prompt.tokens.get_common_prefix(prompt.tokens);
if (cur_lcp_len == (int) prompt.tokens.size()) {
SRV_TRC("%s", " - prompt is already in the cache, skipping\n");
return nullptr;
}
}
// calculate checkpoints size to see if it will fit with the prompt
size_t checkpoints_size = 0;
for (const auto & ckpt : prompt.checkpoints) {
checkpoints_size += ckpt->size();
}
const size_t state_size_new = state_size_tgt + state_size_dft + checkpoints_size;
// skip over-limit entries to avoid disturbing the cache
if (limit_size > 0 && state_size_new > limit_size) {
SRV_WRN(" - prompt state size %.3f MiB exceeds cache size limit %.3f MiB, skipping\n",
state_size_new / (1024.0 * 1024.0), limit_size / (1024.0 * 1024.0));
return nullptr;
}
// remove any cached prompts that are fully contained in the current prompt
for (auto it = states.begin(); it != states.end();) {
const int len = it->prompt.tokens.get_common_prefix(prompt.tokens);
if (len == (int) it->prompt.tokens.size()) {
SRV_TRC(" - removing obsolete cached prompt with length %d\n", len);
it = states.erase(it);
} else {
++it;
}
}
if (limit_size > 0) {
// make room before allocating the new vectors to avoid breaching the limit
while (!states.empty() && size() + state_size_new > limit_size) {
SRV_WRN(" - making room for prompt cache entry, removing oldest entry (size = %.3f MiB)\n",
states.front().size() / (1024.0 * 1024.0));
states.pop_front();
}
}
common_state_data state_data_tgt;
common_state_data state_data_dft;
// check if we can allocate enough memory for the new state
try {
state_data_tgt.resize(state_size_tgt);
state_data_dft.resize(state_size_dft);
} catch (const std::bad_alloc & e) {
SRV_ERR("failed to allocate memory for prompt cache state: %s\n", e.what());
limit_size = std::max<size_t>(1, 0.4*size());
SRV_WRN(" - cache size limit reduced to %.3f MiB\n", limit_size / (1024.0 * 1024.0));
update();
return nullptr;
}
states.push_back({
/*.prompt =*/ {
/*.tokens =*/ prompt.tokens.clone(),
/*.checkpoints =*/ prompt.checkpoints,
},
/*.data =*/ {
/*.main =*/ std::move(state_data_tgt),
/*.drft =*/ std::move(state_data_dft),
},
});
return &states.back();
}
bool server_prompt_cache::load(server_prompt & prompt, const server_tokens & tokens_new, llama_context * ctx_tgt, llama_context * ctx_dft, int32_t id_slot) {
int lcp_best = prompt.tokens.get_common_prefix(tokens_new);
float f_keep_best = prompt.tokens.size() > 0 ? float(lcp_best) / prompt.tokens.size() : -1.0f; // empty slot: any cache entry wins
float f_sim_best = float(lcp_best) / tokens_new.size();
SRV_TRC(" - looking for better prompt, base f_keep = %.3f, f_sim = %.3f\n", f_keep_best, f_sim_best);
auto it_best = states.end();
// find the most similar cached prompt, that would also preserve the most context
for (auto it = states.begin(); it != states.end(); ++it) {
const int lcp_cur = it->prompt.tokens.get_common_prefix(tokens_new);
const float f_keep_cur = float(lcp_cur) / it->prompt.tokens.size();
const float f_sim_cur = float(lcp_cur) / tokens_new.size();
SRV_TRC(" - prompt with length %7zu, lcp = %7d, f_keep = %.3f, f_sim = %.3f\n", it->prompt.tokens.size(), lcp_cur, f_keep_cur, f_sim_cur);
// don't trash large prompts
if (f_keep_cur < 0.25f) {
continue;
}
if (f_keep_best < f_keep_cur && f_sim_best < f_sim_cur) {
f_keep_best = f_keep_cur;
f_sim_best = f_sim_cur;
lcp_best = lcp_cur;
it_best = it;
}
}
if (it_best != states.end()) {
SRV_TRC(" - found better prompt with f_keep = %.3f, f_sim = %.3f\n", f_keep_best, f_sim_best);
{
auto & data = it_best->data.main;
const size_t size = data.size();
const size_t n = llama_state_seq_set_data_ext(ctx_tgt, data.data(), size, id_slot, 0);
if (n != size) {
SRV_ERR("failed to restore state with size %zu\n", size);
return false;
}
data.clear();
data.shrink_to_fit();
}
{
auto & data = it_best->data.drft;
if (!data.empty()) {
GGML_ASSERT(ctx_dft);
const size_t size = data.size();
const size_t n = llama_state_seq_set_data_ext(ctx_dft, data.data(), size, id_slot, 0);
if (n != size) {
SRV_WRN("failed to restore state with size %zu\n", size);
return false;
}
data.clear();
data.shrink_to_fit();
}
}
SRV_DBG("%s", "__TEST_TAG_PROMPT_CACHE_RESTORE__\n");
// the whole cached prompt is a prefix of the new one
if (lcp_best == (int) it_best->prompt.tokens.size()) {
SRV_DBG("%s", "__TEST_TAG_PROMPT_CACHE_FULL_RESTORE__\n");
}
prompt = std::move(it_best->prompt);
states.erase(it_best);
}
return true;
}
void server_prompt_cache::update() {
if (limit_size > 0) {
while (!states.empty() && size() > limit_size) {
SRV_WRN(" - cache size limit reached, removing oldest entry (size = %.3f MiB)\n", states.front().size() / (1024.0 * 1024.0));
states.pop_front();
}
}
// average size per token
const float size_per_token = std::max<float>(1.0f, float(size()) / (std::max<size_t>(1, n_tokens())));
// dynamically increase the token limit if it can fit in the memory limit
const size_t limit_tokens_cur = limit_size > 0 ? std::max<size_t>(limit_tokens, limit_size/size_per_token) : limit_tokens;
if (limit_tokens > 0) {
while (!states.empty() && n_tokens() > limit_tokens_cur) {
SRV_WRN(" - cache token limit (%zu, est: %zu) reached, removing oldest entry (size = %.3f MiB)\n",
limit_tokens, limit_tokens_cur, states.front().size() / (1024.0 * 1024.0));
states.pop_front();
}
}
SRV_TRC(" - cache state: %zu prompts, %.3f MiB (limits: %.3f MiB, %zu tokens, %zu est)\n",
states.size(), size() / (1024.0 * 1024.0), limit_size / (1024.0 * 1024.0), limit_tokens, limit_tokens_cur);
for (const auto & state : states) {
SRV_TRC(" - prompt %p: %7d tokens, checkpoints: %2zu, %9.3f MiB\n",
(const void *)&state, state.prompt.n_tokens(), state.prompt.checkpoints.size(), state.size() / (1024.0 * 1024.0));
}
}