284 Commits

Author SHA1 Message Date
Atream
5ec33d046d optimize gguf dequant, save mem, support Q2_K
use marlin for lm_head, lm_head only calc last token for prefill
extend context window to 19K for DeepSeek-V3/R1 within 24GB VRAM
2025-02-22 06:13:01 +00:00
Atream
7e1fe256c8 optimize GPU 2025-02-21 05:06:57 +00:00
Atream
cf4da5fd47
Merge pull request #382 from ceerRep/server-prefix-cache
fix server and add prefix cache for server
2025-02-19 12:33:36 +08:00
Azure
ea75849d03
Merge pull request #481 from Zhoneym/main
Modify and add any incorrect or missing content in the `install.md`
2025-02-19 11:19:11 +08:00
Zhoneym
c72291832d
Update install.md 2025-02-19 10:39:43 +08:00
Zhoneym
3015e9dfa7
Modify and add any incorrect or missing content in the install.md file. 2025-02-19 10:01:16 +08:00
ceerrep
584c7d5639 fix: object type for non-streaming response 2025-02-18 23:50:28 +08:00
ceerrep
6d45871de8 fix: workaround return dummy usage 2025-02-18 22:39:49 +08:00
ZiWei Yuan
09f5c5e77e
Merge pull request #476 from kvcache-ai/V0.2.1.post1
🔖 release v0.2.1.post1
2025-02-18 21:48:30 +08:00
liam
75d7d423b0 🔖 release v0.2.1.post1 2025-02-18 20:45:48 +08:00
Azure
a435e1bbcd
Merge pull request #406 from hoshinohikari/main
Fix cmake error caused by lack of environment variables in Windows environment
2025-02-18 20:09:59 +08:00
ceerrep
db61375f1a Merge remote-tracking branch 'kvai/main' into server-prefix-cache 2025-02-18 17:51:22 +08:00
Azure
19fd24f461
Merge pull request #412 from haojiubujian1985/delete-unused-link
Update README_ZH.md
2025-02-18 14:58:10 +08:00
Atream
1c1769a579
Merge pull request #413 from kvcache-ai/fix_precision_MLA
Fix precision mla
2025-02-18 14:44:50 +08:00
liam
592e13d453 add mmlu_pro test 2025-02-18 14:43:38 +08:00
Atream
1054ee3ae4
Merge pull request #450 from kvcache-ai/update-WeChatGroup
Add files via upload
2025-02-18 14:34:07 +08:00
Atream
261d5d393f
Add files via upload 2025-02-18 14:28:29 +08:00
Azure
2671fc7f4b
Merge pull request #445 from dedfaf/main
Fix typo in DeepseekR1_V3_tutorial.md Line 174
2025-02-18 14:23:29 +08:00
UnicornChan
ccf0f1910f
Merge pull request #442 from Zhoneym/patch-1
Fix `GLIBCXX_3.4.30' not found in Anaconda
2025-02-18 13:58:44 +08:00
liam
07a0555016 fix device and add test 2025-02-18 12:52:17 +08:00
ceerrep
73d072f609 Merge branch 'fix_precision_MLA' of https://github.com/kvcache-ai/ktransformers into server-prefix-cache 2025-02-18 11:44:28 +08:00
ceerrep
2ffb43f974 fix: adapt prefix cache in forward_linux_flashinfer 2025-02-18 11:40:15 +08:00
Xie Weiyu
f029588b61 fix server warmup 2025-02-18 11:39:45 +08:00
Zhoneym
8b221f532a
Fix `GLIBCXX_3.4.30' not found in Anaconda 2025-02-18 11:32:42 +08:00
ceerrep
c70b6f4d5b fix: use 'cuda:0' by default if torch_device is 'cuda' 2025-02-18 11:15:17 +08:00
dedfaf
3e5c5a2f4a Fix typo in DeepseekR1_V3_tutorial.md Line 174 2025-02-18 10:57:12 +08:00
Xie Weiyu
9f1da18630 update install.sh 2025-02-17 20:50:19 +08:00
Xie Weiyu
c176e516b5 server mix mla 2025-02-17 20:40:28 +08:00
ceerrep
ee24eb8dc3 fix: fix server for triton kernel 2025-02-17 18:08:45 +08:00
ceerrep
bb1cadfff3 Merge branch 'fix_precision_MLA' of https://github.com/kvcache-ai/ktransformers into server-prefix-cache 2025-02-17 18:08:04 +08:00
Atream
038bc30888 fix precision bug imported by position_ids in 0.2.0 2025-02-17 09:23:14 +00:00
xubo
49c6e2fc04 Update README_ZH.md 2025-02-17 16:56:44 +08:00
hoshinohikari
6d9182795c
Fix cmake error caused by lack of environment variables in Windows environment 2025-02-17 15:56:56 +08:00
ceerrep
cd9f7f8f34 fix: server: drop <think> tag in chat template 2025-02-17 14:25:27 +08:00
ceerrep
ca2090d89b feat: use model name in openai endpoint 2025-02-17 00:27:32 +08:00
ceerrep
5ac266085e fix: use flash_attn for faster prefill 2025-02-17 00:11:24 +08:00
ceerrep
bb0ccc7b1a feat: add prefix cache for server 2025-02-17 00:10:55 +08:00
wang jiahao
c515cc49a5
Merge pull request #355 from kvcache-ai/qiyuxinlin-patch-1
Update install.md
2025-02-16 15:05:43 +08:00
wang jiahao
24de607be4
Merge pull request #357 from kvcache-ai/qiyuxinlin-patch-2
Update SUMMARY.md
2025-02-16 15:05:19 +08:00
Atream
b84524622e support bf16 read 2025-02-16 06:43:27 +00:00
wang jiahao
76554dd674
Update SUMMARY.md 2025-02-16 14:30:22 +08:00
wang jiahao
56d19d6115
Update install.md 2025-02-16 14:23:56 +08:00
Azure
9f9c3738f9
Merge pull request #354 from Azure-Tang/fix-mockTritonMLA
[fix] Mock triton mla due to precision issue
2025-02-16 14:06:54 +08:00
Azure
ff6b265e53 Mock triton mla due to precision issue 2025-02-16 06:03:12 +00:00
Atream
c5f036e8a4
Merge pull request #333 from kvcache-ai/feat_experts_gpu
toy support for experts on GPU, no CUDA Graph
2025-02-15 23:30:24 +08:00
Atream
8ed8eb2a9e
Update FAQ.md 2025-02-15 23:27:35 +08:00
Atream
c189d55bd1 toy support for experts on GPU, no CUDA Graph 2025-02-15 15:16:00 +00:00
wang jiahao
ae8da019c1
Merge pull request #330 from hrz6976/fix-nonetype
thanks..., I was about to submit and found that you had already modified it. Thank you for your contribution
2025-02-15 22:50:51 +08:00
Azure
56382aa869
Merge pull request #290 from ZhangShuaiyi/dev/check_gguf_path
ensure that gguf_path argument is a directory.
2025-02-15 22:48:57 +08:00
Azure
c8bf250104
Merge pull request #324 from BiFangKNT/patch-2
Update DeepseekR1_V3_tutorial.md
2025-02-15 22:23:09 +08:00