root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 21:39:52 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity
bb43cf7e9d
llama.cpp/examples/server/tests/features/server.feature

101 lines
4.6 KiB
Gherkin
Raw Normal View History

server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
@llama.cpp
server: tests: passkey challenge / self-extend with context shift demo (#5832) * server: tests: add models endpoint scenario * server: /v1/models add some metadata * server: tests: add debug field in context before scenario * server: tests: download model from HF, add batch size * server: tests: add passkey test * server: tests: add group attention params * server: do not truncate prompt tokens if self-extend through group attention is enabled * server: logs: do not truncate log values * server: tests - passkey - first good working value of nga * server: tests: fix server timeout * server: tests: fix passkey, add doc, fix regex content matching, fix timeout * server: tests: fix regex content matching * server: tests: schedule slow tests on master * server: metrics: fix when no prompt processed * server: tests: self-extend add llama-2-7B and Mixtral-8x7B-v0.1 * server: tests: increase timeout for completion * server: tests: keep only the PHI-2 test * server: tests: passkey add a negative test
2024-03-02 21:00:14 +00:00
@server
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Feature: llama.cpp server
Background: Server startup
Given a server listening on localhost:8080
common: llama_load_model_from_url split support (#6192) * 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>
2024-03-23 17:07:00 +00:00
And a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
And a model file test-model.gguf
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
And a model alias tinyllama-2
And 42 as server seed
# KV Cache corresponds to the total amount of tokens
# that can be stored across all independent sequences: #4130
# see --ctx-size and #5568
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
And 256 KV cache size
And 32 as batch size
And 2 slots
And 64 server max tokens to predict
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708) * server: monitoring - add /metrics prometheus compatible endpoint * server: concurrency issue, when 2 task are waiting for results, only one call thread is notified * server: metrics - move to a dedicated struct
2024-02-25 12:49:43 +00:00
And prometheus compatible metrics exposed
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Then the server is starting
Then the server is healthy
Scenario: Health
Then the server is ready
And all slots are idle
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Scenario Outline: Completion
Given a prompt <prompt>
And <n_predict> max tokens to predict
And a completion request with no api error
Then <n_predicted> tokens are predicted matching <re_content>
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
And the completion is <truncated> truncated
And <n_prompt> prompt tokens are processed
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708) * server: monitoring - add /metrics prometheus compatible endpoint * server: concurrency issue, when 2 task are waiting for results, only one call thread is notified * server: metrics - move to a dedicated struct
2024-02-25 12:49:43 +00:00
And prometheus metrics are exposed
server: metrics: add llamacpp:prompt_seconds_total and llamacpp:tokens_predicted_seconds_total, reset bucket only on /metrics. Fix values cast to int. Add Process-Start-Time-Unix header. (#5937) Closes #5850
2024-03-08 11:25:04 +00:00
And metric llamacpp:tokens_predicted is <n_predicted>
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Examples: Prompts
server tests : more pythonic process management; fix bare `except:` (#6146) * server tests : remove seemingly redundant newlines in print() * server tests : use built-in subprocess features, not os.kill and psutil * server tests : do not catch e.g. SystemExit; use print_exc * server tests: handle TimeoutExpired exception * server tests: fix connect on dual-stack systems * server: tests: add new tokens regex on windows generated following new repeat penalties default changed in (#6127) * server: tests: remove the hack on windows since now we get the good socket family * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) --------- Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-03-20 05:33:49 +00:00
| prompt | n_predict | re_content | n_prompt | n_predicted | truncated |
| I believe the meaning of life is | 8 | (read\|going)+ | 18 | 8 | not |
| Write a joke about AI from a very long prompt which will not be truncated | 256 | (princesses\|everyone\|kids\|Anna\|forest)+ | 46 | 64 | not |
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
Scenario: Completion prompt truncated
Given a prompt:
"""
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
"""
And a completion request with no api error
server tests : more pythonic process management; fix bare `except:` (#6146) * server tests : remove seemingly redundant newlines in print() * server tests : use built-in subprocess features, not os.kill and psutil * server tests : do not catch e.g. SystemExit; use print_exc * server tests: handle TimeoutExpired exception * server tests: fix connect on dual-stack systems * server: tests: add new tokens regex on windows generated following new repeat penalties default changed in (#6127) * server: tests: remove the hack on windows since now we get the good socket family * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) --------- Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-03-20 05:33:49 +00:00
Then 64 tokens are predicted matching fun|Annaks|popcorns|pictry|bowl
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
And the completion is truncated
And 109 prompt tokens are processed
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Scenario Outline: OAI Compatibility
Given a model <model>
And a system prompt <system_prompt>
And a user prompt <user_prompt>
And <max_tokens> max tokens to predict
And streaming is <enable_streaming>
Given an OAI compatible chat completions request with no api error
Then <n_predicted> tokens are predicted matching <re_content>
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
And <n_prompt> prompt tokens are processed
And the completion is <truncated> truncated
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Examples: Prompts
server tests : more pythonic process management; fix bare `except:` (#6146) * server tests : remove seemingly redundant newlines in print() * server tests : use built-in subprocess features, not os.kill and psutil * server tests : do not catch e.g. SystemExit; use print_exc * server tests: handle TimeoutExpired exception * server tests: fix connect on dual-stack systems * server: tests: add new tokens regex on windows generated following new repeat penalties default changed in (#6127) * server: tests: remove the hack on windows since now we get the good socket family * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) --------- Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-03-20 05:33:49 +00:00
| model | system_prompt | user_prompt | max_tokens | re_content | n_prompt | n_predicted | enable_streaming | truncated |
| llama-2 | Book | What is the best book | 8 | (Here\|what)+ | 77 | 8 | disabled | not |
| codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128 | (thanks\|happy\|bird\|Annabyear)+ | -1 | 64 | enabled | |
server: tests: add truncated prompt tests, better kv cache size (#5933) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 09:30:04 +00:00
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
json-schema-to-grammar improvements (+ added to server) (#5978) * json: fix arrays (disallow `[,1]`) * json: support tuple types (`[number, string]`) * json: support additionalProperties (`{[k: string]: [string,number][]}`) * json: support required / optional properties * json: add support for pattern * json: resolve $ref (and support https schema urls) * json: fix $ref resolution * join: support union types (mostly for nullable types I think) * json: support allOf + nested anyOf * json: support any (`{}` or `{type: object}`) * json: fix merge * json: temp fix for escapes * json: spaces in output and unrestricted output spaces * json: add typings * json:fix typo * Create ts-type-to-grammar.sh * json: fix _format_literal (json.dumps already escapes quotes) * json: merge lit sequences and handle negatives {"type": "string", "pattern": "^({\"question\": \"[^\"]+\", \"response\": \"[^\"]+\"}\\n)+$"} * json: handle pattern repetitions * Update json-schema-to-grammar.mjs * Create regex-to-grammar.py * json: extract repeated regexp patterns to subrule * Update json-schema-to-grammar.py * Update json-schema-to-grammar.py * Update json-schema-to-grammar.py * json: handle schema from pydantic Optional fields * Update json-schema-to-grammar.py * Update json-schema-to-grammar.py * Update ts-type-to-grammar.sh * Update ts-type-to-grammar.sh * json: simplify nullable fields handling * json: accept duplicate identical rules * json: revert space to 1 at most * json: reuse regexp pattern subrules * json: handle uuid string format * json: fix literal escapes * json: add --allow-fetch * json: simplify range escapes * json: support negative ranges in patterns * Delete commit.txt * json: custom regex parser, adds dot support & JS-portable * json: rm trailing spaces * Update json-schema-to-grammar.mjs * json: updated server & chat `( cd examples/server && ./deps.sh )` * json: port fixes from mjs to python * Update ts-type-to-grammar.sh * json: support prefixItems alongside array items * json: add date format + fix uuid * json: add date, time, date-time formats * json: preserve order of props from TS defs * json: port schema converter to C++, wire in ./server * json: nits * Update json-schema-to-grammar.cpp * Update json-schema-to-grammar.cpp * Update json-schema-to-grammar.cpp * json: fix mjs implementation + align outputs * Update json-schema-to-grammar.mjs.hpp * json: test C++, JS & Python versions * json: nits + regen deps * json: cleanup test * json: revert from c++17 to 11 * json: nit fixes * json: dirty include for test * json: fix zig build * json: pass static command to std::system in tests (fixed temp files) * json: fix top-level $refs * json: don't use c++20 designated initializers * nit * json: basic support for reserved names `{number:{number:{root:number}}}` * Revamp test cmake to allow args (WORKING_DIRECTORY needed for JSON test) * json: re-ran server deps.sh * json: simplify test * json: support mix of additional props & required/optional * json: add tests for some expected failures * json: fix type=const in c++, add failure expectations for non-str const&enum * json: test (& simplify output of) empty schema * json: check parsing in test + fix value & string refs * json: add server tests for OAI JSON response_format * json: test/fix top-level anyOf * json: improve grammar parsing failures * json: test/fix additional props corner cases * json: fix string patterns (was missing quotes) * json: ws nit * json: fix json handling in server when there's no response_format * json: catch schema conversion errors in server * json: don't complain about unknown format type in server if unset * json: cleaner build of test * json: create examples/json-schema-pydantic-example.py * json: fix date pattern * json: move json.hpp & json-schema-to-grammar.{cpp,h} to common * json: indent 4 spaces * json: fix naming of top-level c++ function (+ drop unused one) * json: avoid using namespace std * json: fix zig build * Update server.feature * json: iostream -> fprintf * json: space before & refs for consistency * json: nits
2024-03-21 11:50:43 +00:00
Scenario Outline: OAI Compatibility w/ response format
Given a model test
And a system prompt test
And a user prompt test
And a response format <response_format>
And 10 max tokens to predict
Given an OAI compatible chat completions request with no api error
Then <n_predicted> tokens are predicted matching <re_content>
Examples: Prompts
| response_format | n_predicted | re_content |
| {"type": "json_object", "schema": {"const": "42"}} | 5 | "42" |
| {"type": "json_object", "schema": {"items": [{"type": "integer"}]}} | 10 | \[ -300 \] |
| {"type": "json_object"} | 10 | \{ " Jacky. |
server: init functional tests (#5566) * server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 11:28:55 +00:00
Scenario: Tokenize / Detokenize
When tokenizing:
"""
What is the capital of France ?
"""
Then tokens can be detokenize
server: tests: passkey challenge / self-extend with context shift demo (#5832) * server: tests: add models endpoint scenario * server: /v1/models add some metadata * server: tests: add debug field in context before scenario * server: tests: download model from HF, add batch size * server: tests: add passkey test * server: tests: add group attention params * server: do not truncate prompt tokens if self-extend through group attention is enabled * server: logs: do not truncate log values * server: tests - passkey - first good working value of nga * server: tests: fix server timeout * server: tests: fix passkey, add doc, fix regex content matching, fix timeout * server: tests: fix regex content matching * server: tests: schedule slow tests on master * server: metrics: fix when no prompt processed * server: tests: self-extend add llama-2-7B and Mixtral-8x7B-v0.1 * server: tests: increase timeout for completion * server: tests: keep only the PHI-2 test * server: tests: passkey add a negative test
2024-03-02 21:00:14 +00:00
Scenario: Models available
Given available models
Then 1 models are supported
Then model 0 is identified by tinyllama-2
Then model 0 is trained on 128 tokens context
Reference in New Issue Copy Permalink