vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

common: llama_load_model_from_url split support (#6192)

Browse source 
* llama: llama_split_prefix fix strncpy does not include string termination
common: llama_load_model_from_url:
 - fix header name case sensitive
 - support downloading additional split in parallel
 - hide password in url

* common: EOL EOF

* common: remove redundant LLAMA_CURL_MAX_PATH_LENGTH definition

* common: change max url max length

* common: minor comment

* server: support HF URL options

* llama: llama_model_loader fix log

* common: use a constant for max url length

* common: clean up curl if file cannot be loaded in gguf

* server: tests: add split tests, and HF options params

* common: move llama_download_hide_password_in_url inside llama_download_file as a lambda

* server: tests: enable back Release test on PR

* spacing

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* spacing

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* spacing

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-23 18:07:00 +01:00 • committed by GitHub
parent 1997577d5e
commit f482bb2e49
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 200 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

13
examples/server/tests/features/steps/steps.py
View file

@ -16,7 +16,6 @@ import numpy as np
import openai
from behave import step
from behave.api.async_step import async_run_until_complete
from huggingface_hub import hf_hub_download
from prometheus_client import parser
@ -39,6 +38,8 @@ def step_server_config(context, server_fqdn, server_port):
context.model_alias = None
context.model_file = None
context.model_hf_repo = None
context.model_hf_file = None
context.model_url = None
context.n_batch = None
context.n_ubatch = None
@ -68,9 +69,9 @@ def step_server_config(context, server_fqdn, server_port):
@step('a model file {hf_file} from HF repo {hf_repo}')
def step_download_hf_model(context, hf_file, hf_repo):
context.model_file = hf_hub_download(repo_id=hf_repo, filename=hf_file)
if context.debug:
print(f"model file: {context.model_file}")
context.model_hf_repo = hf_repo
context.model_hf_file = hf_file
context.model_file = os.path.basename(hf_file)
@step('a model file {model_file}')
@ -1079,6 +1080,10 @@ def start_server_background(context):
server_args.extend(['--model', context.model_file])
if context.model_url:
server_args.extend(['--model-url', context.model_url])
if context.model_hf_repo:
server_args.extend(['--hf-repo', context.model_hf_repo])
if context.model_hf_file:
server_args.extend(['--hf-file', context.model_hf_file])
if context.n_batch:
server_args.extend(['--batch-size', context.n_batch])
if context.n_ubatch: