aboutsummaryrefslogtreecommitdiff
path: root/embed.h
blob: f7048b44a8f194ae3f9044444891882db4bacccb (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
/*
 * embed.h - embed API
 */

#ifndef EMBED_H
#define EMBED_H

/* Public-API export annotation. The libraries are built with
 * -fvisibility=hidden, so only declarations carrying EMBED_API are exported
 * from the shared library; everything else stays internal. */
#ifndef EMBED_API
#if defined(__GNUC__)
#define EMBED_API __attribute__((visibility("default")))
#else
#define EMBED_API
#endif
#endif

#include <stddef.h>
#include <stdint.h>

/* ========================================================================
 * Shared constants and family defaults
 * ======================================================================== */

#define EMBED_VOCAB_SIZE     151936
#define EMBED_HEAD_DIM       128
#define EMBED_MAX_LAYERS     64      /* upper bound for stack arrays */
#define EMBED_CONTEXT_SEPARATOR_TOKEN_ID 151643 /* <|endoftext|> */

/* ========================================================================
 * Model Configuration (populated from config.json at load time)
 * ======================================================================== */

typedef enum {
    EMBED_ATTENTION_BIDIRECTIONAL = 0,
    EMBED_ATTENTION_CAUSAL = 1,
} embed_attention_mode_t;

typedef enum {
    EMBED_POOL_MEAN = 0,
    EMBED_POOL_LAST_TOKEN = 1,
} embed_pooling_mode_t;

typedef struct {
    int hidden_size;
    int n_layers;
    int n_heads;
    int n_kv_heads;
    int head_dim;
    int q_dim;              /* n_heads    * head_dim */
    int kv_dim;             /* n_kv_heads * head_dim */
    int intermediate_size;
    int vocab_size;
    float rms_norm_eps;
    float rope_theta;
    embed_attention_mode_t attention_mode;
    embed_pooling_mode_t pooling_mode;
    int normalize_embeddings;
    /* Qwen3-Embedding pools the last token, which is the tokenizer's
     * <|endoftext|> suffix added by its post-processor - not the model's chat
     * eos_token_id (<|im_end|>). Text frontends append it and resolve the id
     * from the tokenizer exactly like the contextual separator
     * (EMBED_CONTEXT_SEPARATOR_TOKEN_ID is the released-model fallback). The
     * model forward consumes token ids exactly and never appends. */
    int append_terminal_token;
} embed_config_t;

/* ========================================================================
 * Model + workspace ownership
 * ======================================================================== */

typedef struct embed_model embed_model_t;
typedef struct embed_workspace embed_workspace_t;
typedef struct embed_late_model embed_late_model_t;
typedef struct embed_late_workspace embed_late_workspace_t;

typedef struct {
    const int *ids;
    int n_tokens;
} embed_input_t;

typedef struct {
    int start;
    int n_tokens;
} embed_span_t;

typedef struct {
    embed_input_t input;
    const embed_span_t *spans;
    int n_spans;
} embed_context_input_t;

/* ========================================================================
 * API
 * ======================================================================== */

/*
 * Load immutable model data from a directory containing:
 *   config.json                          - model hyperparameters
 *   model.safetensors (or sharded)       - F32 or BF16 weights
 *   vocab.json + merges.txt              - BPE tokenizer
 *
 * Reads config.json to determine model size (0.6B vs 4B).
 * Returns NULL on error.
 */
EMBED_API embed_model_t *embed_model_load(const char *model_dir);

EMBED_API void embed_model_free(embed_model_t *model);

/*
 * Allocate/free mutable scratch buffers for a model. The model must outlive
 * workspaces created from it.
 */
EMBED_API embed_workspace_t *embed_workspace_new(const embed_model_t *model);
EMBED_API void embed_workspace_free(embed_workspace_t *ws);

/* Config accessor for opaque model ownership. */
EMBED_API const embed_config_t *embed_model_config(const embed_model_t *model);

/*
 * Current mutable workspace memory owned by this workspace, in bytes.
 *
 * This includes the workspace struct, scratch buffers, and RoPE cache capacity.
 * It does not include immutable mmap'd model weights.
 */
EMBED_API size_t embed_workspace_nbytes(const embed_workspace_t *ws);

/*
 * Compute embedding for a token sequence.
 *
 *   1. Token embedding lookup
 *   2. N transformer layers (GQA + RoPE + SwiGLU)
 *   3. Final RMSNorm
 *   4. Model-defined pooling and optional L2 normalization
 *
 * pplx-embed-v1 uses bidirectional attention and unnormalized mean pooling.
 * Qwen3-Embedding uses causal attention and normalized last-token pooling.
 * Token IDs are consumed exactly as provided; text frontends append any
 * model-required terminal token before calling this API.
 *
 * Returns malloc'd float[hidden_size] (caller frees). NULL on error.
 */
EMBED_API float *embed_model_encode(const embed_model_t *model, embed_workspace_t *ws,
                        const int *token_ids, int n_tokens);

/*
 * Compute one embedding into caller-provided out[hidden_size].
 * Returns 0 on success, -1 on error.
 */
EMBED_API int embed_model_encode_into(const embed_model_t *model, embed_workspace_t *ws,
                          const int *token_ids, int n_tokens,
                          float *out_embedding);

/*
 * Compute embeddings for a true packed/ragged batch.
 *
 * out_embeddings is caller-provided [batch, hidden_size].
 * Each sequence attends only to tokens from the same input, and RoPE
 * positions restart at zero for every input.
 *
 * Returns 0 on success, -1 on error.
 */
EMBED_API int embed_model_encode_batch(const embed_model_t *model, embed_workspace_t *ws,
                           const embed_input_t *inputs, int batch,
                           float *out_embeddings);

/*
 * Apply the config's pooling mode to packed final hidden states.
 *
 * states is [sum(n_tokens), hidden_size]. seq_lengths contains one positive
 * token count per sequence. The states must already include final RMSNorm.
 */
EMBED_API int embed_pool_batch(const embed_config_t *cfg, const float *states,
                    const int *seq_lengths, int batch,
                    float *out_embeddings);

/*
 * Run the transformer forward pass WITHOUT pooling.
 * Returns the full [n_tokens * hidden_size] output after final RMSNorm.
 * Caller frees the returned buffer.  NULL on error.
 *
 * Useful for contextual (late-chunking) models where you need
 * per-token embeddings before splitting by separator positions.
 */
EMBED_API float *embed_model_forward(const embed_model_t *model, embed_workspace_t *ws,
                          const int *token_ids, int n_tokens);

/*
 * Run the transformer forward pass into caller-provided
 * out_states[n_tokens * hidden_size]. Returns 0 on success, -1 on error.
 */
EMBED_API int embed_model_forward_into(const embed_model_t *model, embed_workspace_t *ws,
                            const int *token_ids, int n_tokens,
                            float *out_states);

/*
 * Pool embeddings from final hidden states.
 *
 * states is [n_tokens, hidden_size], normally produced by
 * embed_model_forward_into(). Each span is mean pooled into
 * out_embeddings[n_spans, hidden_size] without L2 normalization.
 */
EMBED_API int embed_pool_spans(const embed_config_t *cfg, const float *states, int n_tokens,
                    const embed_span_t *spans, int n_spans,
                    float *out_embeddings);

/*
 * Run one contextual sequence and pool selected token spans.
 * Returns 0 on success, -1 on error.
 */
EMBED_API int embed_model_encode_spans(const embed_model_t *model, embed_workspace_t *ws,
                           const int *token_ids, int n_tokens,
                           const embed_span_t *spans, int n_spans,
                           float *out_embeddings);

/*
 * Run a packed/ragged contextual document batch and pool every selected span.
 *
 * Documents attend independently, RoPE positions restart for each document,
 * and out_embeddings contains spans in document order.
 */
EMBED_API int embed_model_encode_spans_batch(const embed_model_t *model,
                                 embed_workspace_t *ws,
                                 const embed_context_input_t *inputs, int batch,
                                 float *out_embeddings);

/*
 * L2-normalize vec[dim] in place.
 *
 * Returns 0 on success. Returns -1 for invalid arguments or a zero-length
 * vector, which cannot be normalized.
 */
EMBED_API int embed_l2_normalize(float *vec, int dim);

/*
 * Cosine similarity between two vectors.
 * Returns 0 for invalid arguments or if either vector has zero length.
 */
EMBED_API float embed_cosine_similarity(const float *a, const float *b, int dim);

/*
 * Late-interaction model API.
 *
 * A late model produces one 128D vector per retained token. The vectors are
 * projected by the snapshot's 1_Dense head and L2-normalized per token by
 * default, matching ColBERT/MaxSim scoring semantics.
 */
EMBED_API embed_late_model_t *embed_late_model_load(const char *model_dir);
EMBED_API void embed_late_model_free(embed_late_model_t *model);

EMBED_API embed_late_workspace_t *embed_late_workspace_new(const embed_late_model_t *model);
EMBED_API void embed_late_workspace_free(embed_late_workspace_t *ws);

EMBED_API const embed_config_t *embed_late_model_config(const embed_late_model_t *model);
EMBED_API int embed_late_model_token_dim(const embed_late_model_t *model);

/*
 * Encode token_ids into out_vectors[n_tokens, token_dim].
 *
 * If normalize is non-zero, every non-zero token vector is L2-normalized.
 */
EMBED_API int embed_late_model_encode_tokens(const embed_late_model_t *model,
                                  embed_late_workspace_t *ws,
                                  const int *token_ids, int n_tokens,
                                  int normalize, float *out_vectors);

/*
 * Sum over query tokens of max dot product against document tokens.
 */
EMBED_API float embed_late_maxsim(const float *query_vectors, int query_tokens,
                       const float *doc_vectors, int doc_tokens,
                       int dim);

/*
 * Score one query against a packed/ragged batch of documents.
 *
 * doc_offsets has docs + 1 entries. Document i is stored in
 * doc_vectors[doc_offsets[i] * dim .. doc_offsets[i + 1] * dim).
 * scores is caller-provided [docs].
 */
EMBED_API int embed_late_maxsim_batch(const float *query_vectors, int query_tokens,
                           const float *doc_vectors,
                           const int *doc_offsets, int docs,
                           int dim, float *scores);

/* Verbose level: 0=quiet, 1=info, 2=debug */
EMBED_API extern int embed_verbose;
EMBED_API extern int qwen_verbose;

#endif /* EMBED_H */