url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

cuda(win): export + load the #111 pipeline ABI — 24 missing DLLEXPORT decorations + loader wrappers, unbreaks CUDA_DLL=1 (#201)

Browse Source 
PR #111 added 24 functions (pipe_*, attention_*_batch*, shared_mlp_w4a16,
tensor_update) to backend_cuda.h without COLI_CUDA_DLLEXPORT and without
backend_loader.c wrappers: on Windows the host failed to link (undefined
references from glm.c) and the DLL exported none of the new entry points.
Decorate the declarations and add matching typedefs/RESOLVEs/wrappers
following the loader's existing pattern. DLL now exports 39 symbols;
engine links; TF oracle 32/32 CPU + dual-GPU (sm_120/sm_89).

Co-authored-by: olorin <io@zyphyr.co>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Tom Olorin
2026-07-14 09:43:56 -07:00
committed by GitHub
parent 3045b35cdd
commit 21cbf14d59
2 changed files with 226 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/backend_cuda.h
+22 -22
View File
@@ -60,7 +60,7 @@ COLI_CUDA_DLLEXPORT int coli_cuda_expert_mlp(ColiCudaTensor *gate, ColiCudaTenso
* memory, activations are converted to FP16 per tile, and Tensor Cores
* accumulate into FP32. Unlike COLI_CUDA_TC_INT4 this does not quantize the
* activation to INT4. */
int coli_cuda_shared_mlp_w4a16(ColiCudaTensor *gate, ColiCudaTensor *up,
COLI_CUDA_DLLEXPORT int coli_cuda_shared_mlp_w4a16(ColiCudaTensor *gate, ColiCudaTensor *up,
ColiCudaTensor *down, float *y,
const float *x, int S);
@@ -97,46 +97,46 @@ COLI_CUDA_DLLEXPORT size_t coli_cuda_tensor_bytes(const ColiCudaTensor *tensor);
COLI_CUDA_DLLEXPORT int coli_cuda_tensor_device(const ColiCudaTensor *tensor);
/* Replace a resident tensor's contents without reallocating its device slot. */
int coli_cuda_tensor_update(ColiCudaTensor *tensor,
COLI_CUDA_DLLEXPORT int coli_cuda_tensor_update(ColiCudaTensor *tensor,
const void *weights, const float *scales);
/* ---- resident-pipeline primitives (Inc.0): device-pointer entry points ---- */
float *coli_cuda_pipe_scratch(int device,int slot,size_t bytes);
void *coli_cuda_pipe_alloc(int device,size_t bytes);
void coli_cuda_pipe_free(int device,void *p);
int coli_cuda_pipe_upload(int device,void *dst,const void *src,size_t bytes);
int coli_cuda_pipe_download(int device,const void *src,void *dst,size_t bytes);
int coli_cuda_pipe_rmsnorm(int device,float *y_dev,const float *x_dev,
COLI_CUDA_DLLEXPORT float *coli_cuda_pipe_scratch(int device,int slot,size_t bytes);
COLI_CUDA_DLLEXPORT void *coli_cuda_pipe_alloc(int device,size_t bytes);
COLI_CUDA_DLLEXPORT void coli_cuda_pipe_free(int device,void *p);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_upload(int device,void *dst,const void *src,size_t bytes);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_download(int device,const void *src,void *dst,size_t bytes);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_rmsnorm(int device,float *y_dev,const float *x_dev,
const float *w_dev,int S,int D,float eps);
int coli_cuda_pipe_rope(int device,float *v_dev,const int *pos_dev,int rows,
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_rope(int device,float *v_dev,const int *pos_dev,int rows,
int stride,int offset,int R,int heads,float theta);
int coli_cuda_pipe_silu_mul(int device,float *gate_dev,const float *up_dev,size_t n);
int coli_cuda_pipe_add(int device,float *x_dev,const float *t_dev,size_t n);
int coli_cuda_pipe_rows_add(int device,float *x_dev,const float *partial_dev,
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_silu_mul(int device,float *gate_dev,const float *up_dev,size_t n);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_add(int device,float *x_dev,const float *t_dev,size_t n);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_rows_add(int device,float *x_dev,const float *partial_dev,
const int *rows_dev,int nrows,int D);
int coli_cuda_pipe_gemm(ColiCudaTensor *t,float *y_dev,const float *x_dev,int S);
int coli_cuda_pipe_rmsnorm_s(int device,float *y_dev,const float *x_dev,
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_gemm(ColiCudaTensor *t,float *y_dev,const float *x_dev,int S);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_rmsnorm_s(int device,float *y_dev,const float *x_dev,
const float *w_dev,int S,int D,float eps,
int xstride,int ystride);
int coli_cuda_pipe_rope_base(int device,float *v_dev,int pos_base,int rows,
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_rope_base(int device,float *v_dev,int pos_base,int rows,
int stride,int offset,int R,int heads,float theta);
int coli_cuda_pipe_copy2d(int device,float *dst,int dpitch,const float *src,
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_copy2d(int device,float *dst,int dpitch,const float *src,
int spitch,int width,int height);
int coli_cuda_attention_project_batch_dev(ColiCudaTensor *kv_b,ColiCudaTensor *o_proj,
COLI_CUDA_DLLEXPORT int coli_cuda_attention_project_batch_dev(ColiCudaTensor *kv_b,ColiCudaTensor *o_proj,
float *out,const float *q_dev,const float *latent_dev,const float *rope_dev,
int S,int H,int Q,int R,int V,int K,int T,float scale);
int coli_cuda_attention_absorb_batch_dev(ColiCudaTensor *kv_b_shard,float *ctx_dev,
COLI_CUDA_DLLEXPORT int coli_cuda_attention_absorb_batch_dev(ColiCudaTensor *kv_b_shard,float *ctx_dev,
const float *q_dev,const float *latent_dev,const float *rope_dev,
int S,int H,int Q,int R,int V,int K,int T,float scale);
int coli_cuda_attention_absorb_kvdev(ColiCudaTensor *kv_b,float *ctx,const float *q,
COLI_CUDA_DLLEXPORT int coli_cuda_attention_absorb_kvdev(ColiCudaTensor *kv_b,float *ctx,const float *q,
const float *latent_dev,const float *rope_dev,int H,int Q,int R,int V,int K,int T,
float scale);
int coli_cuda_pipe_peer_copy(int dst_dev,float *dst,int src_dev,
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_peer_copy(int dst_dev,float *dst,int src_dev,
const float *src,size_t bytes);
int coli_cuda_attention_project_batch_dev_out(ColiCudaTensor *kv_b,ColiCudaTensor *o_proj,
COLI_CUDA_DLLEXPORT int coli_cuda_attention_project_batch_dev_out(ColiCudaTensor *kv_b,ColiCudaTensor *o_proj,
float *out_dev,const float *q_dev,const float *latent_dev,const float *rope_dev,
int S,int H,int Q,int R,int V,int K,int T,float scale);
int coli_cuda_pipe_sync(int device);
COLI_CUDA_DLLEXPORT int coli_cuda_pipe_sync(int device);
#ifdef __cplusplus
}