root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

server : samplers accept the prompt correctly (#10019)
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-musa.Dockerfile platforms:linux/amd64 tag:full-musa]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-musa.Dockerfile platforms:linux/amd64 tag:light-musa]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-musa.Dockerfile platforms:linux/amd64 tag:server-musa]) (push) Waiting to run
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Details
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Details
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Details
Nix CI / nix-build (macos-latest) (push) Waiting to run
Details
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
Details
flake8 Lint / Lint (push) Waiting to run
Details

Browse Source
This commit is contained in:
wwoodsTM 2024-10-23 13:27:51 -06:00 committed by GitHub
parent 190a37d797
commit 0a1c750c80
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
examples/server/server.cpp
View File

@ -2163,17 +2163,10 @@ struct server_context {
GGML_ASSERT(slot.n_prompt_tokens < slot.n_ctx);
}
common_sampler_reset(slot.smpl);
if (slot.params.cache_prompt) {
// reuse any previously computed tokens that are common with the new prompt
slot.n_past = longest_common_prefix(slot.cache_tokens, prompt_tokens);
// push the prompt into the sampling context (do not apply grammar)
for (int i = 0; i < slot.n_past; ++i) {
common_sampler_accept(slot.smpl, slot.cache_tokens[i], false);
}
// reuse chunks from the cached prompt by shifting their KV cache in the new position
if (params.n_cache_reuse > 0) {
size_t head_c = slot.n_past; // cache
@ -2206,8 +2199,6 @@ struct server_context {
for (size_t i = 0; i < n_match; i++) {
slot.cache_tokens[head_p + i] = slot.cache_tokens[head_c + i];
common_sampler_accept(slot.smpl, slot.cache_tokens[head_p + i], false);
slot.n_past++;
}
@ -2259,8 +2250,6 @@ struct server_context {
// there is no common part left
slot.n_past = 0;
common_sampler_reset(slot.smpl);
}
SLT_INF(slot, "kv cache rm [%d, end)\n", slot.n_past);
@ -2288,6 +2277,13 @@ struct server_context {
GGML_ASSERT(batch.n_tokens > 0);
common_sampler_reset(slot.smpl);
// Process all prompt tokens through sampler system
for (int i = 0; i < slot.n_prompt_tokens; ++i) {
common_sampler_accept(slot.smpl, prompt_tokens[i], false);
}
// extract the logits only for the last token
batch.logits[batch.n_tokens - 1] = true;