2023-03-10 19:40:58 +01:00
|
|
|
*.o
|
|
|
|
|
*.a
|
2023-06-28 17:53:37 +02:00
|
|
|
*.so
|
2023-04-19 19:10:08 +02:00
|
|
|
.DS_Store
|
|
|
|
|
.build/
|
2023-03-10 19:40:58 +01:00
|
|
|
.cache/
|
2023-04-19 19:10:08 +02:00
|
|
|
.direnv/
|
|
|
|
|
.envrc
|
|
|
|
|
.swiftpm
|
|
|
|
|
.venv
|
2023-06-06 08:55:10 +02:00
|
|
|
.clang-tidy
|
2023-03-10 19:40:58 +01:00
|
|
|
.vs/
|
|
|
|
|
.vscode/
|
|
|
|
|
|
|
|
|
|
build/
|
|
|
|
|
build-em/
|
|
|
|
|
build-debug/
|
|
|
|
|
build-release/
|
2023-07-18 13:24:43 +02:00
|
|
|
build-ci-debug/
|
|
|
|
|
build-ci-release/
|
2023-03-10 19:40:58 +01:00
|
|
|
build-static/
|
2023-04-26 22:14:13 +02:00
|
|
|
build-cublas/
|
2023-05-13 10:23:15 +02:00
|
|
|
build-opencl/
|
2023-06-04 22:34:30 +02:00
|
|
|
build-metal/
|
2023-07-10 17:49:56 +02:00
|
|
|
build-mpi/
|
2023-03-10 19:40:58 +01:00
|
|
|
build-no-accel/
|
|
|
|
|
build-sanitize-addr/
|
|
|
|
|
build-sanitize-thread/
|
2023-06-16 08:58:11 +02:00
|
|
|
out/
|
2023-07-18 13:24:43 +02:00
|
|
|
tmp/
|
2023-03-10 19:40:58 +01:00
|
|
|
|
2023-03-11 11:26:46 +01:00
|
|
|
models/*
|
2023-07-18 13:24:43 +02:00
|
|
|
models-mnt
|
2023-03-11 11:26:46 +01:00
|
|
|
|
2023-03-10 19:40:58 +01:00
|
|
|
/main
|
|
|
|
|
/quantize
|
2023-04-08 00:09:18 +02:00
|
|
|
/quantize-stats
|
2023-03-17 23:03:48 +01:00
|
|
|
/result
|
2023-03-25 19:26:40 +01:00
|
|
|
/perplexity
|
2023-03-28 17:34:35 +02:00
|
|
|
/embedding
|
2023-06-15 19:42:48 +02:00
|
|
|
/train-text-from-scratch
|
2023-06-17 18:30:22 +02:00
|
|
|
/simple
|
2023-04-30 14:32:37 +02:00
|
|
|
/benchmark-matmult
|
2023-04-18 22:00:08 +02:00
|
|
|
/vdot
|
Server Example Refactor and Improvements (#1570)
A major rewrite for the server example.
Note that if you have built something on the previous server API, it will probably be incompatible.
Check out the examples for how a typical chat app could work.
This took a lot of effort, there are 24 PR's closed in the submitter's repo alone, over 160 commits and a lot of comments and testing.
Summary of the changes:
- adds missing generation parameters: tfs_z, typical_p, repeat_last_n, repeat_penalty, presence_penalty, frequency_penalty, mirostat, penalize_nl, seed, ignore_eos
- applies missing top k sampler
- removes interactive mode/terminal-like behavior, removes exclude parameter
- moves threads and batch size to server command-line parameters
- adds LoRA loading and matches command line parameters with main example
- fixes stopping on EOS token and with the specified token amount with n_predict
- adds server timeouts, host, and port settings
- adds expanded generation complete response; adds generation settings, stop reason, prompt truncated, model used, and final text
- sets defaults for unspecified parameters between requests
- removes /next-token endpoint and as_loop parameter, adds stream parameter and server-sent events for streaming
- adds CORS headers to responses
- adds request logging, exception printing and optional verbose logging
- adds better stopping words handling when matching multiple tokens and while streaming, or when it finishes on a partial stop string
- adds printing an error when it can't bind to the host/port specified
- fixes multi-byte character handling and replaces invalid UTF-8 characters on responses
- prints timing and build info on startup
- adds logit bias to request parameters
- removes embedding mode
- updates documentation; adds streaming Node.js and Bash examples
- fixes code formatting
- sets server threads to 1 since the current global state doesn't work well with simultaneous requests
- adds truncation of the input prompt and better context reset
- removes token limit from the input prompt
- significantly simplified the logic and removed a lot of variables
---------
Co-authored-by: anon998 <131767832+anon998@users.noreply.github.com>
Co-authored-by: Henri Vasserman <henv@hot.ee>
Co-authored-by: Felix Hellmann <privat@cirk2.de>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Lesaun Harvey <Lesaun@gmail.com>
2023-06-17 13:53:04 +02:00
|
|
|
/server
|
2023-03-29 22:51:37 +02:00
|
|
|
/Pipfile
|
2023-06-28 17:53:37 +02:00
|
|
|
/embd-input-test
|
2023-06-06 09:18:03 +02:00
|
|
|
/libllama.so
|
2023-05-01 18:23:47 +02:00
|
|
|
build-info.h
|
2023-03-10 19:40:58 +01:00
|
|
|
arm_neon.h
|
|
|
|
|
compile_commands.json
|
2023-06-16 08:58:11 +02:00
|
|
|
CMakeSettings.json
|
2023-03-17 23:03:48 +01:00
|
|
|
|
2023-03-28 18:39:01 +02:00
|
|
|
__pycache__
|
2023-04-05 17:06:02 +02:00
|
|
|
|
|
|
|
|
zig-out/
|
|
|
|
|
zig-cache/
|
2023-04-19 19:10:08 +02:00
|
|
|
|
|
|
|
|
ppl-*.txt
|
2023-05-08 16:41:54 +02:00
|
|
|
qnt-*.txt
|
2023-05-11 23:23:08 +02:00
|
|
|
perf-*.txt
|
2023-04-28 18:13:33 +02:00
|
|
|
|
|
|
|
|
examples/jeopardy/results.txt
|
2023-07-21 12:09:16 +02:00
|
|
|
|
2023-07-21 12:53:27 +02:00
|
|
|
|
|
|
|
|
pyproject.toml
|
|
|
|
|
poetry.lock
|
|
|
|
|
poetry.toml
|
|
|
|
|
|
2023-07-21 12:09:16 +02:00
|
|
|
# Test binaries
|
|
|
|
|
tests/test-double-float
|
|
|
|
|
tests/test-grad0
|
|
|
|
|
tests/test-opt
|
|
|
|
|
tests/test-quantize-fns
|
|
|
|
|
tests/test-quantize-perf
|
|
|
|
|
tests/test-sampling
|
2023-07-21 13:42:41 +02:00
|
|
|
tests/test-tokenizer-0
|
|
|
|
|
|