refactor: enhance error logging and add HTTP timeout configuration in generator

This commit is contained in:
2026-06-09 21:33:06 +02:00
parent 56c7219bf3
commit 002628497e
2 changed files with 25 additions and 2 deletions

View File

@@ -22,4 +22,6 @@
`llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q4_K_S --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 194 t/s
`llama-server -hf unsloth/gemma-4-E4B-it-GGUF:Q3_K_XL --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 126 t/s
`llama-server -hf unsloth/gemma-4-E4B-it-GGUF:Q3_K_XL --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 126 t/s
`llama-server -hf unsloth/gemma-4-26B-A4B-it-qat-GGUF:UD-Q4_K_XL --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 20 t/s