Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,163 Commits 179 Branches 50 Tags 606 MiB

Default Branch

main

b57f370386 · Saving some VRAM. (#2790) · Updated 2024-12-02 20:04:21 -07:00
 ZIP  TAR.GZ

Branches

feature/no_repeat_ngram_size

12381b0b0e · delete the last no repeat processor from warpers · Updated 2024-07-26 03:22:46 -06:00
309
5
 ZIP  TAR.GZ
add_api_key

169c8c2cf5 · token.to_str() returns result · Updated 2024-07-26 02:52:55 -06:00
357
6
 ZIP  TAR.GZ
use_g6

5afc98a7d7 · Snapshot update with vllm paged. · Updated 2024-07-25 04:17:40 -06:00
283
3
 ZIP  TAR.GZ
feat/max_queue_size

344427b6ab · feat(router): drop permit after batching · Updated 2024-07-23 14:40:14 -06:00
275
1
 ZIP  TAR.GZ
git_v2.2.0

db7e043ded · New version. · Updated 2024-07-23 10:29:13 -06:00
276
1
 ZIP  TAR.GZ
debug/gemma2

0c95f7a942 · Debug softcap flash decoding activation · Updated 2024-07-23 07:12:19 -06:00
280
1
 ZIP  TAR.GZ
fix_mistral2

dee649c60c · Chore: Fix naming issues regarding head_size, there can only be one. · Updated 2024-07-23 03:26:53 -06:00
281
1
 ZIP  TAR.GZ
refactor-lora-linear

82fc879e17 · feat: refactor lora linear and remove adapter layers · Updated 2024-07-18 13:58:55 -06:00
303
1
 ZIP  TAR.GZ
development-guide

a1b69a8cc5 · Completing development guide · Updated 2024-07-18 09:38:18 -06:00
386
2
 ZIP  TAR.GZ
feature/prefix

959b9dc25f · Fixup constructor arguments · Updated 2024-07-17 01:42:24 -06:00
309
16
 ZIP  TAR.GZ
ci_amd3

2967b8168c · fix post refactor · Updated 2024-07-16 07:16:27 -06:00
303
51
 ZIP  TAR.GZ
experiment/moe

f6ad3b3585 · Some MoE exploration · Updated 2024-07-15 05:47:52 -06:00
309
1
 ZIP  TAR.GZ
fix/allow-top-p-0

5b27307438 · Don't error on OpenAI valid `top_p` values. · Updated 2024-07-12 14:22:23 -06:00
309
1
 ZIP  TAR.GZ
ci-new-cluster

5c69639f74 · add condition different than PR · Updated 2024-07-12 05:19:52 -06:00
317
8
 ZIP  TAR.GZ
git_v2.1.1

4dfdb481fb · Version 2.1.1 · Updated 2024-07-04 04:39:07 -06:00
334
1
 ZIP  TAR.GZ
add-small-ttft-script

fe3991e857 · feat: add simple ttft load_test · Updated 2024-07-02 09:57:01 -06:00
339
1
 ZIP  TAR.GZ
test-batch-speedup-amount

cb232a35a9 · feat: add test to view batch speedup amount · Updated 2024-07-02 07:33:26 -06:00
339
1
 ZIP  TAR.GZ
fp8_kvcache

0a5b19a3ed · updated doc · Updated 2024-07-02 07:10:26 -06:00
383
22
 ZIP  TAR.GZ
add-chat-response-format

dea9c0dc74 · Fixing rocm. (#2164) · Updated 2024-07-02 04:01:08 -06:00
341
0
 Included
 ZIP  TAR.GZ
fix-mixtral-adapter-loading

88e2a6a23a · fix: avoid loading mistral adapters in mixtral · Updated 2024-07-01 13:49:05 -06:00
347
1
 ZIP  TAR.GZ