Commit graph

628 commits

Author SHA1 Message Date
Mug
29e9fb66a3 Better llama.cpp interoperability
Has some too many newline issues so WIP

(Update) Fixed too many newlines, now onto args.

Still needs shipping work so you could do "python -m llama_cpp.examples." etc.
2023-05-31 15:25:57 -07:00
Andrei Betlen
ce66405da1 Add quantize example 2023-05-31 15:25:57 -07:00
Mug
739e8d4c9b Fix bug in init_break not being set when exited via antiprompt and others. 2023-05-31 15:25:57 -07:00
Mug
ae1f37f505 Fix repeating instructions and an antiprompt bug 2023-05-31 15:25:57 -07:00
Mug
3c1020b866 Fix stripping instruction prompt 2023-05-31 15:25:57 -07:00
Mug
0bfad75406 Added instruction mode, fixed infinite generation, and various other fixes 2023-05-31 15:25:57 -07:00
Mug
9e872410da Add instruction mode 2023-05-31 15:25:57 -07:00
Mug
15bea0946b Chat llama.cpp example implementation 2023-05-31 15:25:57 -07:00
MillionthOdin16
2b8147e7a8 Update llama_cpp.py 2023-05-31 15:25:57 -07:00
Andrei Betlen
62ce167b22 Update low level api example 2023-05-31 15:25:57 -07:00
Andrei Betlen
a71cda6546 Update llama.cpp 2023-05-31 15:25:57 -07:00
Andrei Betlen
a279acd680 Update llama.cpp (llama_n_embd) 2023-05-31 15:25:57 -07:00
Andrei Betlen
ef3c152257 Update llama.cpp (llama_progress_callback) 2023-05-31 15:25:57 -07:00
Andrei Betlen
def46dd9a6 Add example based on stripped down version of main.cpp from llama.cpp 2023-05-31 15:25:57 -07:00
Andrei Betlen
5bb1bc74d1 Fix type signature of token_to_str 2023-05-31 15:25:57 -07:00
Andrei Betlen
a7a6d88793 Fix ctypes typing issue for Arrays 2023-05-31 15:25:57 -07:00
Andrei Betlen
019650f416 Fix array type signatures 2023-05-31 15:25:57 -07:00
Andrei Betlen
a3da39af79 Bugfix: cross-platform method to find shared lib 2023-05-31 15:24:39 -07:00
Andrei Betlen
bd1c657f80 Bugfix: wrong signature for quantize function 2023-05-31 15:24:10 -07:00
Andrei Betlen
ef5a9a6160 Update llama.cpp and re-organize low-level api 2023-05-31 15:16:27 -07:00
Andrei Betlen
d9dfdec2bd Initial commit (llama_cpp.py, llama-cpp-python) 2023-05-31 15:16:11 -07:00
Henri Vasserman
ffb06a345e
OpenLLaMA 3B support (#1588)
This adds support to llama.cpp to load the model.

Currently missing are changes that are required from convert.py to convert the model correctly. It needs some changes to start reading the JSON configuration for HF models instead of deriving the values by guessing.

Co-authored-by: FNsi <125447286+FNsi@users.noreply.github.com>
2023-05-30 21:24:22 +03:00
Georgi Gerganov
7552ac5863
ggml : sync cgraph import / export API 2023-05-29 19:31:44 +03:00
Georgi Gerganov
5d1830b99d
ggml : fix bug in ggml_alibi 2023-05-29 19:30:49 +03:00
DannyDaemonic
248367605e
Work around for recalculating logits in cached prompts (Fixes #1585) (#1609)
* Work around for recalculating logits in cached prompts
2023-05-29 05:13:40 -07:00
Jiří Podivín
0e730dd23b
Adding git in container package dependencies (#1621)
Git added to build packages for version information in docker image

Signed-off-by: Jiri Podivin <jpodivin@gmail.com>
2023-05-28 21:45:50 -07:00
Johannes Gäßler
3b126f654f
LLAMA_DEBUG adds debug symbols (#1617) 2023-05-28 21:01:02 +02:00
Kerfuffle
1b78ed2081
Only show -ngl option when relevant + other doc/arg handling updates (#1625)
1. Add a `LLAMA_SUPPORTS_GPU_OFFLOAD` define to `llama.h` (defined when compiled with CLBlast or cuBLAS)
2. Update the argument handling in the common example code to only show the `-ngl`, `--n-gpu-layers` option when GPU offload is possible.
3. Add an entry for the `-ngl`, `--n-gpu-layers` option to the `main` and `server` examples documentation
4. Update `main` and `server` examples documentation to use the new style dash separator argument format
5. Update the `server` example to use dash separators for its arguments and adds `-ngl` to `--help` (only shown when compiled with appropriate support). It will still support `--memory_f32` and `--ctx_size` for compatibility.
6. Add a warning discouraging use of `--memory-f32` for the `main` and `server` examples `--help` text as well as documentation. Rationale: https://github.com/ggerganov/llama.cpp/discussions/1593#discussioncomment-6004356
2023-05-28 11:48:57 -06:00
Vladimir Zorin
337aea1139
examples : add --alias option to gpt_params to set use friendly model name (#1614) 2023-05-28 20:14:24 +03:00
Howard Su
bb051d9723
opencl : no need to allocate cl_mem on heap (#1612) 2023-05-28 20:13:36 +03:00
Howard Su
ca74884f66
opencl : use strstr to check if fp16 supported (#1611)
* Use strstr to check if fp16 supported

* Ensure ext_buffer is null terminated
2023-05-28 20:09:56 +03:00
apcameron
a6704643b6
ggml : add support for the RISCV architecture (#1616) 2023-05-27 23:03:25 +03:00
Kerfuffle
0df7d63e5b
Include server in releases + other build system cleanups (#1610)
Set `LLAMA_BUILD_SERVER` in workflow so the `server` example gets build. This currently only applies to Windows builds because it seems like only Windows binary artifacts are included in releases.

Add `server` example target to `Makefile` (still uses `LLAMA_BUILD_SERVER` define and does not build by default)

Fix issue where `vdot` binary wasn't removed when running `make clean`.

Fix compile warnings in `server` example.

Add `.hpp` files to trigger workflow (the server example has one).
2023-05-27 11:04:14 -06:00
Henri Vasserman
97c9b77c4f
Add documentation about CLBlast (#1604)
Installing, compiling and using.
2023-05-27 18:47:55 +03:00
Henri Vasserman
0ecb1bbbeb
[CI] Fix openblas (#1613)
* Fix OpenBLAS build

* Fix `LLAMA_BLAS_VENDOR` CMake variable that should be a string and not a boolean.
2023-05-27 17:24:06 +03:00
Georgi Gerganov
93618031c7
ggml : add ggml_tensor_overhead() 2023-05-27 16:19:56 +03:00
Henri Vasserman
83c54e6da5
[CI] CLBlast: Fix directory name (#1606) 2023-05-27 14:18:25 +02:00
Georgi Gerganov
bdbda1b17a
ggml : sync ggml core (minor additions, e.g. ggml_get_tensor_by_name()) 2023-05-27 12:23:16 +03:00
Kerfuffle
66874d4fbc
Some improvements to loading the session with --prompt-cache (#1550)
Improvements to loading the session with `--prompt-cache` in the `main` example.

1. Fix an issue where the `--seed` parameter was ignored when loading a cached prompt.
2. When loading a cached prompt, you previously had to specify the saved prompt (or a prefix of it) again. This pull changes that behavior to default to the prompt that was cached if a prompt wasn't specified by the user.
2023-05-25 20:18:01 -06:00
Johannes Gäßler
1fcdcc28b1
cuda : performance optimizations (#1530)
* xor hack

* block y dim

* loop unrolling

* Fixed cmake LLAMA_CUDA_BY option

* Removed hipblas compatibility code

* Define GGML_CUDA_DMMV_BLOCK_Y if not defined

* Fewer iters, more ops per iter

* Renamed DMMV X/Y compilation options
2023-05-26 00:07:29 +03:00
Henri Vasserman
ac7876ac20
Update CLBlast to 1.6.0 (#1580)
* Update CLBlast to 1.6.0
2023-05-24 10:30:09 +03:00
Evan Jones
c31bbe934b
readme : add docs for chat-persistent.sh (#1568)
* readme : add docs for chat-persistent.sh

* Update README.md
2023-05-24 09:24:01 +03:00
Senemu
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564) 2023-05-24 09:16:22 +03:00
Maarten ter Huurne
7d873811f3
Fix handling of "invalid property" when creating OpenCL command queue (#1565)
The `clCreateCommandQueue()` function will return the code
`CL_INVALID_QUEUE_PROPERTIES` when passed unsupported properties,
not `CL_INVALID_PROPERTY` as the original code was checking for.
2023-05-23 19:01:15 +03:00
0cc4m
2e6cd4b025
OpenCL Token Generation Acceleration (#1459)
* Move back to C++ for OpenCL

* Refactor OpenCL code to work more like the CUDA code, add missing functions

* Deduplicate dequant kernels

* Add OpenCL compile options

* Use compile args for preprocessing constants

* Restore default platform + device selection by id behavior

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Henri Vasserman <henv@hot.ee>
2023-05-23 00:33:24 +03:00
Steward Garcia
7e4ea5beff
examples : add server example with REST API (#1443)
* Added httplib support

* Added readme for server example

* fixed some bugs

* Fix the build error on Macbook

* changed json11 to nlohmann-json

* removed some whitespaces

* remove trailing whitespace

* added support custom prompts and more functions

* some corrections and added as cmake option
2023-05-21 20:51:18 +03:00
Stefan Sydow
7780e4f479
make : .PHONY clean (#1553) 2023-05-21 17:03:44 +03:00
Georgi Gerganov
265db9834e
ggml : output 3d sizes in ggml_graph_dump_dot() 2023-05-21 11:56:23 +03:00
Georgi Gerganov
fab49c685e
ggml : update WASM SIMD 2023-05-20 20:00:41 +03:00
Zenix
b8ee340abe
feature : support blis and other blas implementation (#1536)
* feature: add blis support

* feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927

* fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake

* Fix typo in INTEGER

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

* Fix: blas changes on ci

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-05-20 17:58:31 +03:00