talk-llama : sync llama.cpp
Some checks failed
Bindings Tests (Ruby) / ubuntu-22 (push) Has been cancelled
CI / determine-tag (push) Has been cancelled
CI / ubuntu-22 (linux/amd64) (push) Has been cancelled
CI / ubuntu-22 (linux/ppc64le) (push) Has been cancelled
CI / ubuntu-22-arm64 (linux/arm64) (push) Has been cancelled
CI / ubuntu-22-arm-v7 (linux/arm/v7) (push) Has been cancelled
CI / macOS-latest (generic/platform=iOS) (push) Has been cancelled
CI / macOS-latest (generic/platform=macOS) (push) Has been cancelled
CI / macOS-latest (generic/platform=tvOS) (push) Has been cancelled
CI / ubuntu-22-gcc (linux/amd64, Debug) (push) Has been cancelled
CI / ubuntu-22-gcc (linux/amd64, Release) (push) Has been cancelled
CI / ubuntu-22-gcc (linux/ppc64le, Debug) (push) Has been cancelled
CI / ubuntu-22-gcc (linux/ppc64le, Release) (push) Has been cancelled
CI / ubuntu-22-gcc-arm64 (linux/arm64, Debug) (push) Has been cancelled
CI / ubuntu-22-gcc-arm64 (linux/arm64, Release) (push) Has been cancelled
CI / ubuntu-22-gcc-arm-v7 (linux/arm/v7, Debug) (push) Has been cancelled
CI / ubuntu-22-gcc-arm-v7 (linux/arm/v7, Release) (push) Has been cancelled
CI / ubuntu-22-clang (linux/amd64, Debug) (push) Has been cancelled
CI / ubuntu-22-clang (linux/amd64, Release) (push) Has been cancelled
CI / ubuntu-22-clang (linux/arm64, Debug) (push) Has been cancelled
CI / ubuntu-22-clang (linux/arm64, Release) (push) Has been cancelled
CI / ubuntu-22-clang (linux/ppc64le, Debug) (push) Has been cancelled
CI / ubuntu-22-clang (linux/ppc64le, Release) (push) Has been cancelled
CI / ubuntu-22-gcc-sanitized (linux/amd64, ADDRESS) (push) Has been cancelled
CI / ubuntu-22-gcc-sanitized (linux/amd64, THREAD) (push) Has been cancelled
CI / ubuntu-22-gcc-sanitized (linux/amd64, UNDEFINED) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl (linux/amd64, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl (linux/arm/v7, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl (linux/arm64, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl (linux/ppc64le, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl-fp16 (linux/amd64, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl-fp16 (linux/arm/v7, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl-fp16 (linux/arm64, icx, icpx, ON) (push) Has been cancelled
CI / ubuntu-22-cmake-sycl-fp16 (linux/ppc64le, icx, icpx, ON) (push) Has been cancelled
CI / windows-msys2 (Release, clang-x86_64, CLANG64) (push) Has been cancelled
CI / windows-msys2 (Release, ucrt-x86_64, UCRT64) (push) Has been cancelled
CI / windows (Win32, Release, win32-x86, x86, 2.28.5, ON) (push) Has been cancelled
CI / windows (x64, Release, win32-x86-64, x64, 2.28.5, ON) (push) Has been cancelled
CI / windows-blas (Win32, ON, x86, 0.3.29, Release, x86, 2.28.5, ON) (push) Has been cancelled
CI / windows-blas (x64, ON, x64_64, 0.3.29, Release, x64, 2.28.5, ON) (push) Has been cancelled
CI / windows-cublas (x64, Release, ON, 11.8.0, ON, 2.28.5) (push) Has been cancelled
CI / windows-cublas (x64, Release, ON, 12.4.0, ON, 2.28.5) (push) Has been cancelled
CI / emscripten (Release) (push) Has been cancelled
CI / ios-xcode-build (Release) (push) Has been cancelled
CI / android (push) Has been cancelled
CI / android_java (push) Has been cancelled
CI / bindings-java (push) Has been cancelled
CI / quantize (push) Has been cancelled
CI / release (push) Has been cancelled
CI / coreml-base-en (push) Has been cancelled
CI / vad (push) Has been cancelled
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/main-intel.Dockerfile platform:linux/amd64 tag:main-intel]) (push) Has been cancelled
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/main-musa.Dockerfile platform:linux/amd64 tag:main-musa]) (push) Has been cancelled
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/main.Dockerfile platform:linux/amd64 tag:main]) (push) Has been cancelled
Examples WASM / deploy-wasm-github-pages (push) Has been cancelled

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-18 10:22:47 +03:00
parent 69061e356f
commit 2f60ebc3c2
26 changed files with 1454 additions and 504 deletions

View File

@ -4,6 +4,7 @@
#include <array>
#include <vector>
#include <set>
// very similar to llama_batch,
// but has more metadata about sequences
@ -18,8 +19,8 @@ struct llama_ubatch {
llama_token * token; // [n_tokens]
float * embd; // [n_embd, n_tokens]
llama_pos * pos; // [n_tokens]
int32_t * n_seq_id; // [n_seqs] // TODO: remove, should belong to only 1 sequence
llama_seq_id ** seq_id; // [n_seqs] // TODO: become llama_seq_id * seq_id;
int32_t * n_seq_id; // [n_seqs]
llama_seq_id ** seq_id; // [n_seqs]
int8_t * output; // [n_tokens]
};
@ -39,8 +40,6 @@ struct llama_sbatch {
size_t n_embd;
bool logits_all; // TODO: remove once lctx.logits_all is removed too
// sorted indices into the batch
std::vector<int64_t> ids;
// batch indices of the output
@ -76,19 +75,45 @@ struct llama_sbatch {
llama_ubatch split_seq(size_t n_ubatch);
llama_sbatch() = default;
llama_sbatch(const llama_batch & batch, size_t n_embd, bool simple_split = false, bool logits_all = false);
llama_sbatch(const llama_batch & batch, size_t n_embd, bool simple_split = false);
};
// temporary allocate memory for the input batch if needed
struct llama_batch_allocr {
struct llama_batch batch;
// a helper for sanitizing and fulfilling a batch
class llama_batch_allocr {
public:
llama_batch_allocr();
// sanitize and auto-gen missing data in the input batch
// memory is optional. if provided will be used to check for sequence continuity and to determine the positions
bool init(
const llama_batch & batch_inp,
const llama_vocab & vocab,
const llama_memory_i * memory,
bool embd_all);
const llama_batch & get_batch() const;
uint32_t get_n_outputs() const;
llama_pos seq_pos_min(llama_seq_id seq_id) const;
llama_pos seq_pos_max(llama_seq_id seq_id) const;
private:
void clear();
llama_batch batch;
uint32_t n_outputs;
std::array<llama_seq_id, 1> seq_id_0 = { 0 }; // default sequence id
std::vector<llama_pos> pos;
std::vector<int32_t> n_seq_id;
std::vector<llama_seq_id *> seq_id;
std::vector<int8_t> logits;
std::vector<int8_t> output;
// optionally fulfill the batch returned by llama_batch_get_one
llama_batch_allocr(struct llama_batch in_batch, llama_pos p0);
std::vector<std::set<llama_pos>> seq_pos; // seq_pos[s]: the set of positions in sequence s
std::vector<std::vector<bool>> seq_cpl; // seq_cpl[s0][s1]: if sequence s0 is coupled to sequence s1
int debug;
};