Match Qwen235 Frontier chunked prefill
This commit is contained in:
@@ -112,6 +112,7 @@ def knobs(config: Config, paths: dict[str, Path], contract: dict, cache: Path, p
|
||||
"batch_size_cap": config.mns,
|
||||
"max_tokens_in_batch": 8192,
|
||||
"long_prefill_token_threshold": 0,
|
||||
"enable_chunked_prefill": True,
|
||||
"block_size": 16,
|
||||
"num_blocks_mode": "explicit",
|
||||
"num_blocks": int(resolved["num_gpu_blocks"]),
|
||||
|
||||
Reference in New Issue
Block a user