aboutsummaryrefslogtreecommitdiff
path: root/pplx_embed_mlx.h
diff options
context:
space:
mode:
authorOnur Gündüz <ogunduz@gmail.com>2026-03-28 21:27:58 +0100
committerOnur Gündüz <ogunduz@gmail.com>2026-03-28 23:10:03 +0100
commitc47e900b94d18cca1bf600e58f10dbcc2e34c1f7 (patch)
treebf7a4247c528841abe71bbbd408eda3ff71b1152 /pplx_embed_mlx.h
parent34e9eefde7870edcc318209738cabb17c71b50ed (diff)
downloadffwd-c47e900b94d18cca1bf600e58f10dbcc2e34c1f7.tar.gz
ffwd-c47e900b94d18cca1bf600e58f10dbcc2e34c1f7.zip
Refactor and enhance pplx_embed and pplx_embed_mlx for improved model support
- Updated `pplx_embed.h` to support new embedding models: `pplx-embed-v1-4b` and `pplx-embed-context-v1-4b`. - Simplified model configuration structure and constants for better maintainability. - Enhanced comments for clarity on model architecture and configuration. - Modified `pplx_embed_mlx.c` to streamline loading of model weights and configuration from `config.json`. - Improved memory management and error handling in the MLX backend. - Updated embedding computation to support dynamic hidden sizes based on model configuration. - Added `pplx_mlx_config` function to retrieve model configuration details. - Updated README.md - Added .gitignore
Diffstat (limited to 'pplx_embed_mlx.h')
-rw-r--r--pplx_embed_mlx.h15
1 files changed, 7 insertions, 8 deletions
diff --git a/pplx_embed_mlx.h b/pplx_embed_mlx.h
index 5327fd0..a1544ef 100644
--- a/pplx_embed_mlx.h
+++ b/pplx_embed_mlx.h
@@ -1,9 +1,7 @@
/*
* pplx_embed_mlx.h - MLX GPU backend for pplx-embed inference
*
- * Uses Apple's mlx-c to run the transformer on Metal GPU.
- * All operations run on the GPU default stream; the result is copied
- * back to CPU as a float* embedding.
+ * Uses Apple's mlx-c to run the transformer on Metal.
*/
#ifndef PPLX_EMBED_MLX_H
@@ -11,25 +9,26 @@
#include <stddef.h>
#include <stdint.h>
+#include "pplx_embed.h"
/* Opaque MLX model context */
typedef struct pplx_mlx_ctx pplx_mlx_ctx_t;
/*
- * Load model into MLX arrays from safetensors in model_dir.
+ * Load model into MLX arrays from safetensors + config.json.
* Returns NULL on error.
*/
pplx_mlx_ctx_t *pplx_mlx_load(const char *model_dir);
-/*
- * Free all MLX resources.
- */
void pplx_mlx_free(pplx_mlx_ctx_t *ctx);
/*
* Compute embedding for token_ids[0..n_tokens-1].
- * Returns malloc'd float[1024] (caller frees). NULL on error.
+ * Returns malloc'd float[hidden_size] (caller frees). NULL on error.
*/
float *pplx_mlx_embed(pplx_mlx_ctx_t *ctx, const int *token_ids, int n_tokens);
+/* Get the config (so main.c can read hidden_size etc.) */
+const pplx_config_t *pplx_mlx_config(const pplx_mlx_ctx_t *ctx);
+
#endif /* PPLX_EMBED_MLX_H */