Text Ranking
sentence-transformers
Safetensors
Transformers
multilingual
t5gemma2
text2text-generation
reranker
encoder-decoder
FBNL
Retrieval
RAG
cosyy commited on
Commit
cf8089c
·
verified ·
1 Parent(s): 6efb0ad

Update vllm_support/README.md

Browse files
Files changed (1) hide show
  1. vllm_support/README.md +0 -11
vllm_support/README.md CHANGED
@@ -266,14 +266,3 @@ requires `yes -> 4443` and `no -> 1904`.
266
  Reduce `batch_size`, `document_max_length`, `query_max_length`,
267
  `max_model_len`, or `gpu_memory_utilization`.
268
 
269
- **CUDA initialization fails with error 803**
270
-
271
- The process may be resolving a CUDA compatibility library before the host
272
- driver library. On common Debian/Ubuntu layouts, retry with:
273
-
274
- ```bash
275
- export LD_LIBRARY_PATH="/lib/x86_64-linux-gnu:/usr/lib/x86_64-linux-gnu${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
276
- ```
277
-
278
- The provided `start_online_server.sh` applies this adjustment automatically
279
- when both directories exist.
 
266
  Reduce `batch_size`, `document_max_length`, `query_max_length`,
267
  `max_model_len`, or `gpu_memory_utilization`.
268