 AlpinDale
|
73177656ed
feat: quant_llm support (#755)
|
hace 5 meses |
|
AlpinDale
|
ad181e3fef
feat: bring back dynatemp (#754)
|
hace 5 meses |
|
AlpinDale
|
6329c2d53f
chore: re-enable custom token bans (#751)
|
hace 5 meses |
 Ahmed
|
55261b09d6
ci: fix docs deployment (#750)
|
hace 5 meses |
|
Ahmed
|
aecd80a47b
Merge pull request #749 from PygmalionAI/ci/fix-pnpm-install
|
hace 5 meses |
|
Ahmed
|
4435a443e1
ci: fix dep install using pnpm
|
hace 5 meses |
|
AlpinDale
|
abd9d5799a
feat: add XTC Sampling (#740)
|
hace 5 meses |
|
AlpinDale
|
4434c4db84
chore: refactor llama3 rope (#748)
|
hace 5 meses |
|
AlpinDale
|
9d9722b1c1
fix: metrics endpoint with RPC server (#747)
|
hace 5 meses |
|
AlpinDale
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
hace 5 meses |
|
AlpinDale
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 5 meses |
|
AlpinDale
|
1068597e8a
fix: minor bug fixes & clean-ups (#744)
|
hace 5 meses |
 Geun, Lim
|
08711d2ac9
feat: add Exaone model support (#743)
|
hace 5 meses |
|
AlpinDale
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
hace 5 meses |
|
AlpinDale
|
5559c5886f
fix: clear engine ref in RPC server (#738)
|
hace 5 meses |
|
AlpinDale
|
ef3a0f4cb1
fix: `custom_ar` check (#737)
|
hace 5 meses |
|
AlpinDale
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
hace 5 meses |
|
AlpinDale
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
hace 5 meses |
|
AlpinDale
|
d9d85eeb6e
chore: register lora functions as torch ops (#732)
|
hace 5 meses |
|
AlpinDale
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
hace 5 meses |
|
AlpinDale
|
d34e083c48
feat: add experts_int8 support (#730)
|
hace 5 meses |
|
AlpinDale
|
b0f262eec1
feat: FP8 quantization support for AMD ROCm (#729)
|
hace 5 meses |
|
AlpinDale
|
c744443679
ci: bump to 0.6.1.post1 (#728)
|
hace 6 meses |
 miku448
|
9c0e7d95c8
fix: libcudart path for some versions of pytorch (#726)
|
hace 6 meses |
|
AlpinDale
|
4648f16c84
chore: fix return statement in Detokenizer class (#727)
|
hace 6 meses |
|
AlpinDale
|
a286adaeaa
feat: launch API server with uvloop (#725)
|
hace 6 meses |
|
AlpinDale
|
60b702a827
chore: register custom torch ops for flash-attn and flashinfer (#724)
|
hace 6 meses |
|
AlpinDale
|
8e0d376f1c
ci: bump aphrodite to 0.6.1 (#722)
|
hace 6 meses |
|
AlpinDale
|
12e40ae6fd
chore: update grafana template (#721)
|
hace 6 meses |
|
AlpinDale
|
61c7182491
feat: enable prompt logprobs in OpenAI API (#720)
|
hace 6 meses |
