radu/LLamaRecipes @ c9ae01445935ca7ca5f7a9297d4bf5540256ef79

ИН на ревизия: c9ae014459

+refs/pull/572/head

Adding_open_colab

Fix-broken-format-in-preview-for-RAG-chatbo-example

Getting_to_know_Llama

HamidShojanazeri-patch-1

IgorKasianenko-patch-1

IgorKasianenko-patch-2

IgorKasianenko-patch-3

LG3-nits-after-launch

Multi-Modal-RAG-Demo

Remove-Tokenizer-onPrem-vllm-InferenceThroughput

Tool_Calling_Demos

add-old-dirs

add-promptguard-to-safety-checkers

adding_examples_with_aws

albertodepaola-patch-1

albertodepaola-patch-2

amitsangani-patch-1

archive-main

aws-do-fsdp

azure-api-example

benchmark-inference-throughput-cloud-api

book-character-mindmap

carljparker/ignore-429-in-link-check

chat-completion-fix

chat_pipeline

chat_prompt_fix

chatbot

chatbot-recipe

chatbot-with-llama

chauhang-patch-1

check-public

chester-rag-chatbot-example

cmodi-meta-patch-1

codellama-70b

coding-assistant

connect_notebook_update

connortreacy-patch-1

connortreacy-patch-2

connortreacy-patch-3

cuda_profiler

dan/add-groq-cookbook-recipes

dan/add-groq-recipes

dan/fix-llama3-cookbook-example

data-tool

dead_link_fix

demos-4-llama3

demos4llama3v2

demos4llama3v3

demos4llama3v4

demos4llama3v5

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/aiohttp-3.13.4

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/filelock-3.20.3

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/idna-3.15

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/pygments-2.20.0

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/python-dotenv-1.2.2

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/requests-2.33.0

dependabot/pip/end-to-end-use-cases/whatsapp_llama_4_bot/urllib3-2.7.0

deployment

dir-change

dlai_agents

dlai_agents_colab_links

eval_harness

feat/tool_usage_prompt

feature/custom_dataset

feature/fsdp2

feature/length_based_batch_sampling

feature/oasst1_dataset

feature/package_distribution

feature/peft_quickstart_nb

feature/technical-blog-generator

fix-file

fix-lg-notebook-broken-dep-on-llama

fix-package-naming

fix-raft-dataset

fix-step-1

fix/amp_training

fix/contribution.md

fix/custom_dataset_chat_template

fix/dependabot-security-alerts

fix/image-link-whatsapp-llama4

fix/invalidate_label_for_chat

fix/load_model_with_torch_dtype_auto

fix/make_tests_run_on_cpu_instance

fix/max_length

fix/missing_copyright_headers

fix/missing_license_header

fix/no_cuda_in_test_finetuning

fix/plotting-json

fix/prefix_and_adapter_peft

fix/remove_deprecated_pytest_cmdline_preparse

fix/remove_pkg_resources

fix/test_on_cpu_only

fix/unit_test_3.2

fix/unit_tests

fix/update_octoai_model_names

fix/use_package_in_quickstart_notebook

fix/vocab_size_mismatch_inference

fix_alpaca

fix_chat_example

fix_duplicate_model_load

fix_eval

fix_local_links

fix_readme

fixes

fiximport

fixing-readme-links

fixing_chat_example

flop_counter

flop_counter_gc

fsdp-eks

fsdp-qlora

fsdp_lmm

fsdp_optimizer_overlap

ft-fw

ft-fw-2

generating-codebase-docs

gmagent

hotfix_pytest_cpu_gha_runner

ibm-wxai

image-finetuning

init27-patch-1

init27-patch-2

l3-update

leaderboardv2

lg-example-fix

llama-triage-tool

llama4_eval

llama4_ft

llama_4_api_recipes

llama_4_api_release

llamaguard-notebook-colab-link-fix

main

move_resposible_ai

optimizer_overlap

padding_updates

peft-update

pia-refactor

pptx_to_transcript

prompt-migration

prompt-ops-refactor

purpla_llama_typo_fix

qlora-fsdp

rag_update

readme_update

refactor-main

refactor/move_folders

release/0.0.1

release/0.0.4.post1

release/v0.0.4

remove-duplicate-blog-generator

remove-warnings-from-reqs

research-paper-analyser

researcher

revert-profiling

rework-lg-notebook

sagemaker-demo

shorfix

small-patch

ssdp

struc_parser

subramen-patch-1

subramen-patch-2

subramen-patch-3

subramen-patch-4

subramen-patch-5

subramen-patch-6

subramen-patch-7

summarization

suraj-refactor-patch

text2sql

torchtune

transfer_experiment

transformers-version-updated

update-android-app

update-aws-recipes-folder

update-prompt-guard-tutorial

update-video

varunfb-patch-1

varunfb-patch-2

vertexNotebooks

zero-to-llama

Matthias Reso c9ae014459 Enable pipeline parallelism through use of AsyncLLMEngine in vllm inferecen + enable use of lora adapter		преди 1 година
..
inference.py	c9ae014459 Enable pipeline parallelism through use of AsyncLLMEngine in vllm inferecen + enable use of lora adapter	преди 1 година