 Olivier Chafik
|
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)
|
il y a 11 mois |
 Xuan-Son Nguyen
|
63ac128563
server : add TEI API format for /rerank endpoint (#11942)
|
il y a 11 mois |
 Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
il y a 11 mois |
|
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
il y a 11 mois |
 Daniel Bevenius
|
5598f475be
server : remove CPPHTTPLIB_NO_EXCEPTIONS define (#11622)
|
il y a 11 mois |
|
Olivier Chafik
|
bfcce4d693
`tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585)
|
il y a 11 mois |
|
Olivier Chafik
|
a83f528688
`tool-call`: fix llama 3.x and functionary 3.2, play nice w/ pydantic_ai package, update readme (#11539)
|
il y a 11 mois |
|
Olivier Chafik
|
b1bcd309fc
fix stop regression (#11543)
|
il y a 11 mois |
|
Olivier Chafik
|
4a2b196d03
server : fix --jinja when there's no tools or schema (typo was forcing JSON) (#11531)
|
il y a 11 mois |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
il y a 11 mois |
|
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
il y a 1 an |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
il y a 1 an |
|
Georgi Gerganov
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
il y a 1 an |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
il y a 1 an |
|
Xuan Son Nguyen
|
0da5d86026
server : allow using LoRA adapters per-request (#10994)
|
il y a 1 an |
|
Xuan Son Nguyen
|
45095a61bf
server : clean up built-in template detection (#11026)
|
il y a 1 an |
|
Xuan Son Nguyen
|
5896c65232
server : add OAI compat for /v1/completions (#10974)
|
il y a 1 an |
 Reza Kakhki
|
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
|
il y a 1 an |
 NeverLucky
|
09fe2e7613
server: allow filtering llama server response fields (#10940)
|
il y a 1 an |
|
Xuan Son Nguyen
|
485dc01214
server : add system_fingerprint to chat/completion (#10917)
|
il y a 1 an |
|
Xuan Son Nguyen
|
57bb2c40cd
server : fix logprobs, make it OAI-compatible (#10783)
|
il y a 1 an |
|
Xuan Son Nguyen
|
46828872c3
server : (embeddings) using same format for "input" and "content" (#10872)
|
il y a 1 an |
 krystiancha
|
05c3a444b8
server : fill usage info in embeddings and rerank responses (#10852)
|
il y a 1 an |
 Michelle Tan
|
89d604f2c8
server: Fix `has_next_line` in JSON response (#10818)
|
il y a 1 an |
 kallewoof
|
484d2f31ae
bug-fix: snprintf prints NULL in place of the last character (#10419)
|
il y a 1 an |
|
Xuan Son Nguyen
|
3573fa8e7b
server : (refactor) no more json in server_task input (#10691)
|
il y a 1 an |
|
Georgi Gerganov
|
ce4a7b8493
server : various fixes (#10704)
|
il y a 1 an |
|
Xuan Son Nguyen
|
6c5bc0625f
server : (refactoring) do not rely on JSON internally (#10643)
|
il y a 1 an |
 haopeng
|
64ed2091b2
server: Add "tokens per second" information in the backend (#10548)
|
il y a 1 an |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
il y a 1 an |
