fit-params : refactor + add option to output estimated memory per device (#22171)

* fit-params : add option to output estimated memory per device

* cont : minor

* cont : refactor

* cont : move fit params implementation to libcommon

* cont : header

* cont : headers

* cont : codeowners

Author: ggerganov

CODEOWNERS

@@ -23,6 +23,7 @@
 /ci/                                    @ggerganov
 /cmake/                                 @ggerganov
 /common/                                @ggml-org/llama-common
+/common/fit.*                           @JohannesGaessler
 /common/jinja/                          @CISC
 /common/ngram-map.*                     @srogmann
 /convert_*.py                           @CISC

common/CMakeLists.txt

@@ -73,6 +73,8 @@ add_library(${TARGET}
     debug.h
     download.cpp
     download.h
+    fit.cpp
+    fit.h
     hf-cache.cpp
     hf-cache.h
     http.h

common/arg.cpp

@@ -2426,6 +2426,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             }
         }
     ).set_env("LLAMA_ARG_FIT"));
+    add_opt(common_arg(
+        { "-fitp", "--fit-print" }, "[on|off]",
+        string_format("print the estimated required memory ('on' or 'off', default: '%s')", params.fit_params_print ? "on" : "off"),
+        [](common_params & params, const std::string & value) {
+            if (is_truthy(value)) {
+                params.fit_params_print = true;
+            } else if (is_falsey(value)) {
+                params.fit_params_print = false;
+            } else {
+                throw std::runtime_error(
+                    string_format("error: unknown value for --fit-print: '%s'\n", value.c_str()));
+            }
+        }
+    ).set_examples({LLAMA_EXAMPLE_FIT_PARAMS}).set_env("LLAMA_ARG_FIT_ESTIMATE"));
     add_opt(common_arg(
         { "-fitt", "--fit-target" }, "MiB0,MiB1,MiB2,...",
         string_format("target margin per device for --fit, comma-separated list of values, "

common/common.cpp

@@ -3,6 +3,7 @@
 
 #include "build-info.h"
 #include "common.h"
+#include "fit.h"
 #include "log.h"
 #include "llama.h"
 #include "sampling.h"
@@ -1147,7 +1148,7 @@ common_init_result::common_init_result(common_params & params) :
 
     if (params.fit_params) {
         LOG_INF("%s: fitting params to device memory, for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on\n", __func__);
-        llama_params_fit(params.model.path.c_str(), &mparams, &cparams,
+        common_fit_params(params.model.path.c_str(), &mparams, &cparams,
             params.tensor_split,
             params.tensor_buft_overrides.data(),
             params.fit_params_target.data(),

common/common.h

@@ -420,11 +420,12 @@ struct common_params {
     // offload params
     std::vector<ggml_backend_dev_t> devices; // devices to use for offloading
 
-    int32_t n_gpu_layers       = -1;   // number of layers to store in VRAM, -1 is auto, <= -2 is all
-    int32_t main_gpu           = 0;    // the GPU that is used for scratch and small tensors
-    float   tensor_split[128]  = {0};  // how split tensors should be distributed across GPUs
-    bool    fit_params         = true; // whether to fit unset model/context parameters to free device memory
-    int32_t fit_params_min_ctx = 4096; // minimum context size to set when trying to reduce memory use
+    int32_t n_gpu_layers       = -1;    // number of layers to store in VRAM, -1 is auto, <= -2 is all
+    int32_t main_gpu           = 0;     // the GPU that is used for scratch and small tensors
+    float   tensor_split[128]  = {0};   // how split tensors should be distributed across GPUs
+    bool    fit_params         = true;  // whether to fit unset model/context parameters to free device memory
+    bool    fit_params_print   = false; // print the estimated required memory to run the model
+    int32_t fit_params_min_ctx = 4096;  // minimum context size to set when trying to reduce memory use
 
     // margin per device in bytes for fitting parameters to free memory:
     std::vector<size_t> fit_params_target = std::vector<size_t>(llama_max_devices(), 1024 * 1024*1024);