Tune prefill batching across Qwen profiles
This commit is contained in:
+4
-4
@@ -105,9 +105,9 @@ services:
|
||||
- --threads-batch
|
||||
- "${LLAMA_THREADS_BATCH:-6}"
|
||||
- --batch-size
|
||||
- "${FAST_BATCH_SIZE:-64}"
|
||||
- "${FAST_BATCH_SIZE:-2048}"
|
||||
- --ubatch-size
|
||||
- "${FAST_UBATCH_SIZE:-32}"
|
||||
- "${FAST_UBATCH_SIZE:-64}"
|
||||
- --parallel
|
||||
- "${FAST_PARALLEL_SLOTS:-1}"
|
||||
- --kv-unified
|
||||
@@ -269,7 +269,7 @@ services:
|
||||
- --batch-size
|
||||
- "${LARGE_BATCH_SIZE:-2048}"
|
||||
- --ubatch-size
|
||||
- "${LARGE_UBATCH_SIZE:-128}"
|
||||
- "${LARGE_UBATCH_SIZE:-256}"
|
||||
- --parallel
|
||||
- "${LARGE_PARALLEL_SLOTS:-1}"
|
||||
- --kv-unified
|
||||
@@ -431,7 +431,7 @@ services:
|
||||
- --batch-size
|
||||
- "${UNCENSORED_BATCH_SIZE:-2048}"
|
||||
- --ubatch-size
|
||||
- "${UNCENSORED_UBATCH_SIZE:-128}"
|
||||
- "${UNCENSORED_UBATCH_SIZE:-256}"
|
||||
- --parallel
|
||||
- "${UNCENSORED_PARALLEL_SLOTS:-1}"
|
||||
- --kv-unified
|
||||
|
||||
Reference in New Issue
Block a user