ochafik
ee6166af73
json: cleanup test
2024-03-12 03:55:14 +00:00
ochafik
917b5d2260
json: nits + regen deps
2024-03-12 03:51:32 +00:00
ochafik
7e1440cc01
Merge branch 'json-fixes-cpp' into json-fixes
2024-03-12 03:48:38 +00:00
ochafik
192a58a5d3
json: test C++, JS & Python versions
2024-03-12 03:46:55 +00:00
ochafik
a740bfacad
Update json-schema-to-grammar.mjs.hpp
2024-03-12 02:09:07 +00:00
ochafik
0be059def8
json: fix mjs implementation + align outputs
2024-03-12 02:08:07 +00:00
ochafik
8fee84b45c
Update json-schema-to-grammar.cpp
2024-03-12 02:06:48 +00:00
ochafik
8caaf1641d
Update json-schema-to-grammar.cpp
2024-03-12 00:02:45 +00:00
ochafik
d934adccea
Update json-schema-to-grammar.cpp
2024-03-11 23:09:51 +00:00
ochafik
cb364ef542
Merge branch 'json-fixes' into json-fixes-cpp
2024-03-11 22:23:19 +00:00
Olivier Chafik
51ca7cb863
json: nits
2024-03-11 22:20:19 +00:00
Olivier Chafik
d0dd75c902
json: port schema converter to C++, wire in ./server
2024-03-11 22:19:26 +00:00
Olivier Chafik
b816734c17
json: preserve order of props from TS defs
2024-03-11 11:48:08 +00:00
ochafik
e1ed7a04d6
json: add date, time, date-time formats
2024-03-11 04:03:05 +00:00
ochafik
9a61802a28
json: add date format + fix uuid
2024-03-11 02:58:14 +00:00
ochafik
d736e928d2
json: support prefixItems alongside array items
2024-03-11 02:32:58 +00:00
ochafik
56b8744158
Update ts-type-to-grammar.sh
2024-03-11 02:11:22 +00:00
ochafik
c8254e5f8a
json: port fixes from mjs to python
2024-03-11 02:10:48 +00:00
ochafik
4e2d06c741
json: updated server & chat ( cd examples/server && ./deps.sh )
2024-03-11 01:51:26 +00:00
ochafik
5389820453
Update json-schema-to-grammar.mjs
2024-03-11 01:47:22 +00:00
ochafik
11813a6b0a
json: rm trailing spaces
2024-03-11 00:27:50 +00:00
ochafik
0e9494183b
json: custom regex parser, adds dot support & JS-portable
2024-03-11 00:24:34 +00:00
ochafik
27b1fefdf4
Delete commit.txt
2024-03-10 17:44:46 +00:00
ochafik
478f62ef5c
json: support negative ranges in patterns
2024-03-10 17:35:32 +00:00
ochafik
d1fda6f450
json: simplify range escapes
2024-03-10 17:32:45 +00:00
ochafik
f57b467c74
json: add --allow-fetch
2024-03-10 17:20:05 +00:00
ochafik
54291e10d0
json: fix literal escapes
2024-03-10 17:19:27 +00:00
ochafik
e8f25d6f0c
json: handle uuid string format
2024-03-10 16:50:06 +00:00
ochafik
37b59d1d3b
json: reuse regexp pattern subrules
2024-03-10 16:49:53 +00:00
ochafik
e8b78c28eb
json: revert space to 1 at most
2024-03-10 16:49:15 +00:00
ochafik
ade339d55e
json: accept duplicate identical rules
2024-03-10 16:48:56 +00:00
ochafik
dab2ea91a6
json: simplify nullable fields handling
2024-03-10 16:48:27 +00:00
ochafik
8597caa685
Update ts-type-to-grammar.sh
2024-03-10 15:47:03 +00:00
ochafik
364bf9ec3d
Update ts-type-to-grammar.sh
2024-03-10 15:44:51 +00:00
ochafik
5764d9ffbc
Update json-schema-to-grammar.py
2024-03-10 15:33:59 +00:00
ochafik
ee492c9e4d
Merge remote-tracking branch 'origin/master' into json-fixes
2024-03-10 15:01:23 +00:00
ochafik
307110ad2c
Update json-schema-to-grammar.py
2024-03-10 15:00:07 +00:00
ochafik
f37ad0a043
json: handle schema from pydantic Optional fields
2024-03-10 14:55:03 +00:00
Georgi Gerganov
c78541479c
nix: update flake.lock ( #5969 )
...
Flake lock file updates:
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/1536926ef5621b09bba54035ae2bb6d806d72ac8' (2024-02-29)
→ 'github:NixOS/nixpkgs/9df3e30ce24fd28c7b3e2de0d986769db5d6225d' (2024-03-06)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-03-10 16:43:08 +02:00
ochafik
ba57964f92
Update json-schema-to-grammar.py
2024-03-10 14:42:39 +00:00
ochafik
b061de52a7
Update json-schema-to-grammar.py
2024-03-10 13:49:27 +00:00
ochafik
259f3505bc
Update json-schema-to-grammar.py
2024-03-10 13:38:40 +00:00
ochafik
1cde8ded7c
json: extract repeated regexp patterns to subrule
2024-03-10 13:29:56 +00:00
ochafik
add8fee04a
Create regex-to-grammar.py
2024-03-10 13:23:00 +00:00
Pierrick Hymbert
621e86b331
server: benchmark: chat/completions scenario and other llm servers comparison ( #5941 )
...
* server: bench: Init a bench scenario with K6
See #5827
* server: bench: EOL EOF
* server: bench: PR feedback and improved k6 script configuration
* server: bench: remove llamacpp_completions_tokens_seconds as it include prompt processing time and it's misleading
server: bench: add max_tokens from SERVER_BENCH_MAX_TOKENS
server: bench: increase truncated rate to 80% before failing
* server: bench: fix doc
* server: bench: change gauge custom metrics to trend
* server: bench: change gauge custom metrics to trend
server: bench: add trend custom metrics for total tokens per second average
* server: bench: doc add an option to debug http request
* server: bench: filter dataset too short and too long sequences
* server: bench: allow to filter out conversation in the dataset based on env variable
* server: bench: fix assistant message sent instead of user message
* server: bench: fix assistant message sent instead of user message
* server : add defrag thold parameter
* server: bench: select prompts based on the current iteration id not randomly to make the bench more reproducible
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 23:41:49 +01:00
Georgi Gerganov
77d1ac7e00
server : print chat template info
2024-03-09 22:04:00 +02:00
slaren
d894f352bf
perplexity : support using multiple sequences to allow larger batch sizes ( #5946 )
...
* perplexity : support using multiple sequences to allow larger batch sizes
ggml-ci
* set cparams.n_parallel to the number of sequences
* print tested n_ctx, add assert
2024-03-09 19:55:54 +01:00
Georgi Gerganov
098dbaab44
readme : update hot topics
2024-03-09 18:14:13 +02:00
Georgi Gerganov
8380ecfb21
ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) ( #5951 )
2024-03-09 17:36:20 +02:00
Georgi Gerganov
58308a0ecc
server : fix metrics init ( #5964 )
2024-03-09 17:34:15 +02:00
