server : check that the prompt fits in the slot's context (ggml-org#10030)

ggml-ci

Author: ggerganov

convert_hf_to_gguf.py

@@ -573,6 +573,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         if chkhsh == "0876d13b50744004aa9aeae05e7b0647eac9d801b5ba4668afc01e709c15e19f":
             # ref: https://huggingface.co/BAAI/bge-small-en-v1.5
             res = "bert-bge"
+        if chkhsh == "8e62295832751ca1e8f92f2226f403dea30dc5165e448b5bfa05af5340c64ec7":
+            # ref: https://huggingface.co/BAAI/bge-large-zh-v1.5
+            res = "bert-bge-large"
         if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
             # ref: https://huggingface.co/mosaicml/mpt-7b
             res = "mpt"

convert_hf_to_gguf_update.py

@@ -72,6 +72,7 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "deepseek-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base", },
     {"name": "falcon",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/falcon-7b", },
     {"name": "bert-bge",       "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/BAAI/bge-small-en-v1.5", },
+    {"name": "bert-bge-large", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/BAAI/bge-large-zh-v1.5", },
     {"name": "mpt",            "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mosaicml/mpt-7b", },
     {"name": "starcoder",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigcode/starcoder2-3b", },
     {"name": "gpt-2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },

examples/server/server.cpp

@@ -1882,12 +1882,17 @@ struct server_context {
                         }
 
                         if (slot.inf_type == SERVER_TASK_INF_TYPE_EMBEDDING || slot.inf_type == SERVER_TASK_INF_TYPE_RERANK) {
-                            // this prompt is too large to process - discard it
                             if (slot.n_prompt_tokens > n_ubatch) {
                                 slot.release();
                                 send_error(slot, "input is too large to process. increase the physical batch size", ERROR_TYPE_SERVER);
                                 continue;
                             }
+
+                            if (slot.n_prompt_tokens > slot.n_ctx) {
+                                slot.release();
+                                send_error(slot, "input is larger than the max context size. skipping", ERROR_TYPE_SERVER);
+                                continue;
+                            }
                         } else {
                             if (!params.ctx_shift) {
                                 // if context shift is disabled, we make sure prompt size is smaller than KV size