Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update doc.

This commit is contained in:
Nicolas Patry 2024-10-21 14:57:24 +02:00
parent a1aac7843b
commit 79469f5f39
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/reference/launcher.md
View File

@ -146,7 +146,7 @@ Options:
## MAX_INPUT_TOKENS ## MAX_INPUT_TOKENS
```shell ```shell
--max-input-tokens <MAX_INPUT_TOKENS> --max-input-tokens <MAX_INPUT_TOKENS>
This is the maximum allowed input length (expressed in number of tokens) for users. The larger this value, the longer prompt users can send which can impact the overall memory required to handle the load. Please note that some models have a finite range of sequence they can handle. Default to min(max_position_embeddings - 1, 4095) This is the maximum allowed input length (expressed in number of tokens) for users. The larger this value, the longer prompt users can send which can impact the overall memory required to handle the load. Please note that some models have a finite range of sequence they can handle. Default to min(max_allocatable, max_position_embeddings) - 1
[env: MAX_INPUT_TOKENS=] [env: MAX_INPUT_TOKENS=]
@ -162,7 +162,7 @@ Options:
## MAX_TOTAL_TOKENS ## MAX_TOTAL_TOKENS
```shell ```shell
--max-total-tokens <MAX_TOTAL_TOKENS> --max-total-tokens <MAX_TOTAL_TOKENS>
This is the most important value to set as it defines the "memory budget" of running clients requests. Clients will send input sequences and ask to generate `max_new_tokens` on top. with a value of `1512` users can send either a prompt of `1000` and ask for `512` new tokens, or send a prompt of `1` and ask for `1511` max_new_tokens. The larger this value, the larger amount each request will be in your RAM and the less effective batching can be. Default to min(max_position_embeddings, 4096) This is the most important value to set as it defines the "memory budget" of running clients requests. Clients will send input sequences and ask to generate `max_new_tokens` on top. with a value of `1512` users can send either a prompt of `1000` and ask for `512` new tokens, or send a prompt of `1` and ask for `1511` max_new_tokens. The larger this value, the larger amount each request will be in your RAM and the less effective batching can be. Default to min(max_allocatable, max_position_embeddings)
[env: MAX_TOTAL_TOKENS=] [env: MAX_TOTAL_TOKENS=]