Martin Evans
09bc688b3c
Skipped slow test again
2 years ago
Martin Evans
cdf20d3c7a
Added timing to stateless test
2 years ago
Martin Evans
7e3cde4c13
Moved helper methods into `LLamaBatchSafeHandle`
2 years ago
Martin Evans
ccb8afae46
Cleaned up stateless executor as preparation for changing it to use the new batched decoding system.
2 years ago
Martin Evans
d8434ea9d6
Merge pull request #185 from martindevans/wip_major_api_change
Major llama.cpp API Change
2 years ago
Martin Evans
1f8c94e386
Added in the `special` parameter to the tokenizer (introduced in https://github.com/ggerganov/llama.cpp/pull/3538 )
2 years ago
Martin Evans
efb0664df0
- Added new binaries
- Fixed stateless executor out-of-context handling
- Fixed token tests
2 years ago
Martin Evans
45118520fa
- Improved coverage of `GBNFGrammarParser` up to 96%
- Covered text transforms
- Removed unnecessary non-async transforms
2 years ago
Martin Evans
2a38808bca
- Added threads to context params, replaced all thread args with `uint?`
- Replaced all binaries
2 years ago
Martin Evans
0d40338692
Fixed out-of-context handling in stateless executor
2 years ago
Martin Evans
3f80190f85
Minimal changes required to remove non-async inference.
2 years ago
Martin Evans
0c98ae1955
Passing ctx to `llama_token_nl(_ctx)`
2 years ago
Martin Evans
a9e6f21ab8
- Creating and destroying contexts in the stateless executor, saving memory. It now uses zero memory when not inferring!
- Passing encoding in the `IModelParams`, which reduces how often encoding needs to be passed around
2 years ago
Martin Evans
48bc0a6f8a
Doe the same for the second test, hopefully fixing CI
2 years ago
Martin Evans
6f2ab8e039
Not asserting the answer, just that it didn't change
2 years ago
Martin Evans
e7b217f462
Fixed out of context logic
2 years ago
Martin Evans
4738c26299
- Reduced context size of test, to speed it up
- Removed some unnecessary `ToArray` calls
- Initial pass on LLamaStatelessExecutor, the context overflow management is broken but I think I found where it's ported from
2 years ago
Martin Evans
4d0c044b9f
Added tests for the StatelessExecutor, one is currently failing
2 years ago