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

server : parallel decoding and multimodal (#3677)

Browse source 
* implementing parallel decoding in server example

* crash fixed

* save dev progress

* refactored sampling function

* completion endpoint working

* multiple client support

* grammar + no stream completion

* cached prompt support

* chat.mjs support cached prompt + some fixes

* server ui now support multiple clients

* unused change reverted

* fixed timings per slot

* add context swap

* add changes to README.md

* llava multimodal integration

* fixed tokens probs

* add multimodal input - alfa

* refactor code + remove unused comments + improved README.md

* fix compilation errors with llvm

* notify the user from server ui that multimodality is unavialable

* some ci fixes

* fix ci make build undefined ref errors

* fix long prompt than ctx proposed in #3639

* fixed premature end due stop word

* context shift fixed

* fix llava implementation

* sync README.md changes

* readme change

* update api like OpenAI

* multimodal support enabled by default

* fix make bui;d errors

* fix multiple clients

* fix zig build

* new sampling API

* latest changes of sampling API

* server : coding-style normalization

* server : coding-style normalization (part 2)

* server : remove beam-search functionality

* server : bug fix in ingest_images

n_tokens is incremented internally by llama_batch_add

* server : use refs + use llama_batch_clear()

* server : snake case

* server : minor sync

* added thread safe pipeline

* server : bach has to be allocated for n_parallel sequences

* server : no need for atomic int - already using mutex

* server : logs + minor code style

* server : fix multibyte handle in partial response (#3706)

* fix image load + view image in chat

* make : silence stb warnings

* clip : link to ggml, not to llama

* server : fix switch fallthrough

* server : fix crash in Debug on macOS (I have no idea why this fixes it!?)

* server : refactor ctx_sampling init + n_ctx + names

* server : bug fix for prompt caching

* Do not save/load image_data to localStorage

* editorconfig : new line in index.html

* server : completion requests remember slot_id

* Update readme to document multimodal in server

* server : minor style

* Update readme to document multimodal in server

* server : hide ctx_sampling->prev behind API (#3696)

* server : apply fix from #3722

* server : fix slot reuse

* server : add comment about changing slot_state to bool

---------

Co-authored-by: FSSRepo <go778sgt@gmail.com>
Co-authored-by: Damian Stewart <d@damianstewart.com>
Co-authored-by: Steward Garcia <57494570+FSSRepo@users.noreply.github.com>
Co-authored-by: Jhen-Jie Hong <iainst0409@gmail.com>
Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
This commit is contained in:
Georgi Gerganov 2023-10-22 22:53:08 +03:00 • committed by GitHub
parent 9e70cc0322
commit 438c2ca830
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
12 changed files with 3980 additions and 2950 deletions
Download patch file Download diff file Expand all files Collapse all files

11
examples/server/chat.mjs
View file

@ -7,6 +7,11 @@ const args = process.argv.slice(2);
const grammarJsonSchemaFile = args.find(
(_, index) => args[index - 1] === "--grammar-json-schema"
);
const no_cached_prompt = args.find(
(_, index) => args[index - 1] === "--no-cache-prompt"
) ?? "false";
const grammarFile = args.find((_, index) => args[index - 1] === "--grammar");
// Example usage: function,arguments
@ -30,6 +35,9 @@ if (grammarFile) {
grammar = readFileSync(grammarFile, 'utf-8')
}
// for cached prompt
let slot_id = -1;
const API_URL = 'http://127.0.0.1:8080'
const chat = [
@ -76,6 +84,8 @@ async function chat_completion(question) {
top_p: 0.9,
n_keep: n_keep,
n_predict: 256,
cache_prompt: no_cached_prompt === "false",
slot_id: slot_id,
stop: ["\n### Human:"], // stop completion after generating this
grammar,
stream: true,
@ -92,6 +102,7 @@ async function chat_completion(question) {
const t = Buffer.from(chunk).toString('utf8')
if (t.startsWith('data: ')) {
const message = JSON.parse(t.substring(6))
slot_id = message.slot_id
answer += message.content
process.stdout.write(message.content)
if (message.stop) {