CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported (#16987)

Browse Source 
* support older socs where FASTRPC_GET_URI is unsupported

* added graceful fallback when FASTRPC_GET_URI call fails

* use weak symbols instead of loading libcdsprpc.so dynamically

* Add weak pragma for rpcmem_alloc2

* Remove weak declaration for rpcmem_alloc2 in ggml-hexagon.cpp

Removed weak declaration for rpcmem_alloc2.

* Enforce ndev to 1 for archs below v75

Force ndev to 1 for SoCs architectures lower than v75.
This commit is contained in:
l3utterfly
2025-11-06 13:46:38 +08:00
committed by GitHub
parent 230d1169e5
commit 6db3d1ffe6
2 changed files with 23 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
ggml/src/ggml-hexagon/ggml-hexagon.cpp
View File

@@ -367,7 +367,13 @@ struct ggml_backend_hexagon_buffer_context {
ggml_backend_hexagon_buffer_context(ggml_hexagon_session * sess, size_t size, bool repack) {
size += 4 * 1024; // extra page for padding
this->base = (uint8_t *) rpcmem_alloc2(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
if (rpcmem_alloc2) {
this->base = (uint8_t *) rpcmem_alloc2(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
} else {
GGML_LOG_INFO("ggml-hex: %s rpcmem_alloc2 not found, falling back to rpcmem_alloc\n", sess->name.c_str());
this->base = (uint8_t *) rpcmem_alloc(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
}
if (!this->base) {
GGML_LOG_ERROR("ggml-hex: %s failed to allocate buffer : size %zu\n", sess->name.c_str(), size);
throw std::runtime_error("ggml-hex: rpcmem_alloc failed (see log for details)");
@@ -1679,12 +1685,13 @@ void ggml_hexagon_session::allocate(int dev_id) noexcept(false) {
}
// Get session URI
char htp_uri[256];
sprintf(htp_uri, "file:///libggml-htp-v%u.so?htp_iface_skel_handle_invoke&_modver=1.0", opt_arch);
char session_uri[256];
{
struct remote_rpc_get_uri u;
char htp_uri[256];
snprintf(htp_uri, sizeof(htp_uri), "file:///libggml-htp-v%u.so?htp_iface_skel_handle_invoke&_modver=1.0", opt_arch);
struct remote_rpc_get_uri u = {};
u.session_id = this->session_id;
u.domain_name = const_cast<char *>(CDSP_DOMAIN_NAME);
u.domain_name_len = strlen(CDSP_DOMAIN_NAME);
@@ -1695,8 +1702,12 @@ void ggml_hexagon_session::allocate(int dev_id) noexcept(false) {
int err = remote_session_control(FASTRPC_GET_URI, (void *) &u, sizeof(u));
if (err != AEE_SUCCESS) {
GGML_LOG_ERROR("ggml-hex: failed to get URI for session %d : error 0x%x\n", dev_id, err);
throw std::runtime_error("ggml-hex: remote_session_control(get-uri) failed (see log for details)");
// fallback to single session uris
int htp_URI_domain_len = strlen(htp_uri) + MAX_DOMAIN_NAMELEN;
snprintf(session_uri, htp_URI_domain_len, "%s%s", htp_uri, my_domain->uri);
GGML_LOG_WARN("ggml-hex: failed to get URI for session %d : error 0x%x. Falling back to single session URI: %s\n", dev_id, err, session_uri);
}
}
@@ -3668,6 +3679,11 @@ ggml_hexagon_registry::ggml_hexagon_registry(ggml_backend_reg_t reg) {
}
}
if(opt_arch < 75) {
opt_ndev = 1;
GGML_LOG_WARN("ggml-hex: forcing ndev to 1 for SoCs archs lower than v75.\n");
}
GGML_LOG_INFO("ggml-hex: Hexagon Arch version v%d\n", opt_arch);
// Create devices / sessions

1
ggml/src/ggml-hexagon/htp-utils.h
View File

@@ -64,6 +64,7 @@ extern "C" {
# pragma weak remote_handle64_control
# pragma weak fastrpc_mmap
# pragma weak fastrpc_munmap
# pragma weak rpcmem_alloc2
#endif
#if !defined(_WINDOWS)