Spaces:
Runtime error
Runtime error
Commit History
-
Optimize model loading and disable speculative decoding for CPU stability
Sagar3ec513c -
Disable flash_attn by default for CPU stability
Sagar1d7babc -
Fix GZipMiddleware import/usage spelling
Sagar64ef5ac -
Optimize LLM CPU infrastructure: standardize configuration, integrate GzipMiddleware, and optimize KV cache
Sagar560cbb7 -
Fix generator StopIteration future exception by implementing sentinel wrapper
Sagar828f20f -
Optimize LLM CPU inference (eager load, 8-bit cache, flash attention, lock, health endpoint)
Sagar017fb0d
-
fix: set context to 16k for stability
e1fcb36 -
fix: restore 32k context and fix library conflict in requirements.txt
3c25a03 -
fix: set context to 5120 and add file verification logic
82efa78 -
debug: reduce n_ctx to 2048 and enable verbose logging
4d6b43d -
fix: optimize n_ctx and threads for low-RAM CPU space
5cf1d7b -
fix: correct model repo and filename for Qwen 2.5 1.5B
f0c4e58 -
fix: switch to docker sdk to use pre-built wheels and avoid OOM
7cb03ae -
fix: downgrade to python 3.11 to avoid OOM build errors
eceedb3 -
docs: add mandatory README.md with space metadata
1085ad0 -
fix: add missing llama-cpp-python dependency and disable flash_attn for CPU
f8e6095 -
Initial commit for SBIG Dispatch Brain v1
132db06