 drummerv
|
e59dd4a90d
fix: openai gguf chat template (#312)
|
vor 10 Monaten |
 AlpinDale
|
c2d77b1822
chore: logging refactor (#302)
|
vor 10 Monaten |
 Pyroserenus
|
951077de65
chore: update klite.embd with current version (#296)
|
vor 10 Monaten |
|
AlpinDale
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
vor 10 Monaten |
|
AlpinDale
|
f35d15e632
fix: arg detection for kobold api launch (#286)
|
vor 10 Monaten |
|
AlpinDale
|
23a7fd8cda
remove ooba endpoint, fix and add deprecation warning for kobold endpoint, fix case where kobold endpoint was always launched with openai (#284)
|
vor 10 Monaten |
|
AlpinDale
|
9fa99215f8
feat: add cubic sampling (#280)
|
vor 10 Monaten |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
vor 10 Monaten |
|
AlpinDale
|
4d04ade9ef
feat: fine-grained seeds (#279)
|
vor 10 Monaten |
 swadical
|
0527131e93
fix: grammar logits processor (#268)
|
vor 10 Monaten |
|
AlpinDale
|
d2db4143fa
feat: add grafana for metrics (#240)
|
vor 11 Monaten |
|
AlpinDale
|
1c46fa31ad
feat: add quadratic sampling (#233)
|
vor 11 Monaten |
|
AlpinDale
|
0adab894fe
feat: grammar support (#206)
|
vor 11 Monaten |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
vor 11 Monaten |
|
AlpinDale
|
3188d5690c
fix: logprobs at -inf (#219)
|
vor 11 Monaten |
 Stefan Gligorijevic
|
56446a04bb
feat: dynamic temperature (#209)
|
vor 11 Monaten |
|
AlpinDale
|
f121a5edd8
feat: tokenizer endpoint for OpenAI API (#195)
|
vor 1 Jahr |
|
AlpinDale
|
b9b295d74e
chore: backlogs 1 (#191)
|
vor 1 Jahr |
|
AlpinDale
|
6eb0b926fd
chore: make openai api key optional (#176)
|
vor 1 Jahr |
|
AlpinDale
|
6c50f5b067
chore: include stop strings in output (#168)
|
vor 1 Jahr |
|
AlpinDale
|
844aec2544
fix: prompt logprobs (#162)
|
vor 1 Jahr |
|
AlpinDale
|
a92f63d8c0
fix: OpenAI chat - reference before assignment (#160)
|
vor 1 Jahr |
|
AlpinDale
|
87277c76e4
feat: Mixtral 8x7B support (#155)
|
vor 1 Jahr |
|
AlpinDale
|
81e7981dce
feat: add prometheus production metrics (#154)
|
vor 1 Jahr |
|
AlpinDale
|
62b2c4119d
feat: re-write GPTQ and refactor exllama kernels (#152)
|
vor 1 Jahr |
|
AlpinDale
|
8ed7d56305
feat: OpenAI chat completions templates (#138)
|
vor 1 Jahr |
|
AlpinDale
|
9d4e437df9
fix: make llama2 the default sep style (#137)
|
vor 1 Jahr |
 AlpinDale
|
05298f1120
properly disable log requests
|
vor 1 Jahr |
|
AlpinDale
|
3459f1c185
feat: usage stats for OpenAI endpoint (#122)
|
vor 1 Jahr |
|
AlpinDale
|
e7b6a2d5a0
chore: tensor parallel refactors part 2 (#116)
|
vor 1 Jahr |
