-
Notifications
You must be signed in to change notification settings - Fork 203
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Enable NeuralChat Unit Test process #195
Commits on Aug 30, 2023
-
Enable NeuralChat Unit Test process
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 17b37d2 - Browse repository at this point
Copy the full SHA 17b37d2View commit details -
* initial commit of n_head_kv in MQA Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com> * add attn ln Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com> * reorder QKV weight when convert Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com> * fix typo Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com> * cherry-pick ggml MQA Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com> * fix kv cache and reduce handmade mem buffer size Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com> --------- Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6739406 - Browse repository at this point
Copy the full SHA 6739406View commit details -
upgrade transformers/hpu docker image/optimum habana version (#186)
no need to maintain mpt model any more in itrex (contained in transformers 4.32.0) Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> Co-authored-by: Haihao Shen <haihao.shen@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 411a589 - Browse repository at this point
Copy the full SHA 411a589View commit details -
* Update README.md Update the readme * Update README.md * Update README.md * Update README.md
Configuration menu - View commit details
-
Copy full SHA for 9a5055e - Browse repository at this point
Copy the full SHA 9a5055eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 54c0a8e - Browse repository at this point
Copy the full SHA 54c0a8eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 1a378c2 - Browse repository at this point
Copy the full SHA 1a378c2View commit details
Commits on Aug 31, 2023
-
Configuration menu - View commit details
-
Copy full SHA for bba7b5c - Browse repository at this point
Copy the full SHA bba7b5cView commit details -
* Update README.md * Refine the collaboration Signed-off-by: hshen14 <haihao.shen@intel.com> --------- Signed-off-by: hshen14 <haihao.shen@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 5f42455 - Browse repository at this point
Copy the full SHA 5f42455View commit details -
refine code-generation example (#192)
* refine code-generation example Signed-off-by: changwangss <chang1.wang@intel.com> * remove code Signed-off-by: changwangss <chang1.wang@intel.com> * remove invalid code * improve readme and line length Signed-off-by: changwangss <chang1.wang@intel.com> --------- Signed-off-by: changwangss <chang1.wang@intel.com> Co-authored-by: Haihao Shen <haihao.shen@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 61145db - Browse repository at this point
Copy the full SHA 61145dbView commit details
Commits on Sep 3, 2023
-
* add gptq examples Signed-off-by: YIYANGCAI <yiyang.cai@intel.com> --------- Signed-off-by: YIYANGCAI <yiyang.cai@intel.com> Co-authored-by: xinhe <xin3.he@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 2427234 - Browse repository at this point
Copy the full SHA 2427234View commit details -
add SKIP_RUNTIME and RUNTIME_ONLY in setup (#182)
* add OPTIMIZATION_ONLY for setup Signed-off-by: Xin He <xin3.he@intel.com> * change name: backends to runtime Signed-off-by: Xin He <xin3.he@intel.com> --------- Signed-off-by: Xin He <xin3.he@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 309a3cf - Browse repository at this point
Copy the full SHA 309a3cfView commit details -
Revert "add SKIP_RUNTIME and RUNTIME_ONLY in setup (#182)"
This reverts commit 120e233.
Configuration menu - View commit details
-
Copy full SHA for acf5def - Browse repository at this point
Copy the full SHA acf5defView commit details -
add finetuning test for mpt-7b-chat with hpu (#204)
Signed-off-by: jiafu zhang <jiafu.zhang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b4c4f9d - Browse repository at this point
Copy the full SHA b4c4f9dView commit details -
llama 70b AutoTP inference (#202)
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9e71158 - Browse repository at this point
Copy the full SHA 9e71158View commit details -
Refine Inference Workflow Readme (#214)
* Refine Inference Workflow Readme --------- Signed-off-by: hshen14 <haihao.shen@intel.com> Co-authored-by: lvliang-intel <liang1.lv@intel.com> Co-authored-by: Wang, Chang <chang1.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 588b124 - Browse repository at this point
Copy the full SHA 588b124View commit details -
add inference test for llama-2-7b-chat-hf and mpt-7b-chat with hpu (#201
Configuration menu - View commit details
-
Copy full SHA for 50d31fc - Browse repository at this point
Copy the full SHA 50d31fcView commit details -
change docker image build dir for hpu (#218)
* add finetuning test for mpt-7b-chat with hpu Signed-off-by: jiafu zhang <jiafu.zhang@intel.com> --------- Signed-off-by: jiafu zhang <jiafu.zhang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 4af5e58 - Browse repository at this point
Copy the full SHA 4af5e58View commit details -
[CPP Graph] add s8 perchannel quant and kernel. (#181)
* add s8 perchannel quant and kernel. * add QKV , add fusion support for s8 PerN * add amx_int8 pern gelu fusion * add gelu add fusion for vnni * split jblas file. add compute type fp32. * add comp_type fp32 for ffn fusion * add bf16 for s4 and s4 ffn fusion * add workspace for jblas functions * keep one jblas code * disable mmap as default. change arg --no_mmap to --use_mmap.
Configuration menu - View commit details
-
Copy full SHA for 9415671 - Browse repository at this point
Copy the full SHA 9415671View commit details -
Configuration menu - View commit details
-
Copy full SHA for cc46d39 - Browse repository at this point
Copy the full SHA cc46d39View commit details -
add SKIP_RUNTIME and RUNTIME_ONLY in setup (#212)
* add OPTIMIZATION_ONLY for setup Signed-off-by: Xin He <xin3.he@intel.com> * change name: backends to runtime Signed-off-by: Xin He <xin3.he@intel.com> * fix bug Signed-off-by: Xin He <xin3.he@intel.com> --------- Signed-off-by: Xin He <xin3.he@intel.com>
Configuration menu - View commit details
-
Copy full SHA for abdcc45 - Browse repository at this point
Copy the full SHA abdcc45View commit details -
neural_chat support torch.float32 (#217)
* Update generate.py * limit autocast Signed-off-by: changwangss <chang1.wang@intel.com> * update readme Signed-off-by: Lv, Liang1 <liang1.lv@intel.com> * update readme Signed-off-by: Lv, Liang1 <liang1.lv@intel.com> * Unify the BKC settings Signed-off-by: hshen14 <haihao.shen@intel.com> * Unify the BKC settings Signed-off-by: hshen14 <haihao.shen@intel.com> * Simplify docker file readme Signed-off-by: hshen14 <haihao.shen@intel.com> * Format the readme Signed-off-by: hshen14 <haihao.shen@intel.com> * Add short description Signed-off-by: hshen14 <haihao.shen@intel.com> --------- Signed-off-by: changwangss <chang1.wang@intel.com> Signed-off-by: Lv, Liang1 <liang1.lv@intel.com> Signed-off-by: hshen14 <haihao.shen@intel.com> Co-authored-by: Lv, Liang1 <liang1.lv@intel.com> Co-authored-by: hshen14 <haihao.shen@intel.com>
Configuration menu - View commit details
-
Copy full SHA for ecb7a09 - Browse repository at this point
Copy the full SHA ecb7a09View commit details -
Configuration menu - View commit details
-
Copy full SHA for 55940e3 - Browse repository at this point
Copy the full SHA 55940e3View commit details -
Configuration menu - View commit details
-
Copy full SHA for 71eff46 - Browse repository at this point
Copy the full SHA 71eff46View commit details -
* refine reademe * refine reademe * refine table * Refine LLM Runtime readme Signed-off-by: hshen14 <haihao.shen@intel.com> * Continue updating the readme Signed-off-by: hshen14 <haihao.shen@intel.com> * Simplify the readme Signed-off-by: hshen14 <haihao.shen@intel.com> * add back run_llm.py * change script arg name * rename arg * fix * add description * add another way to convert model * remove additional line * refine readme * refine readme, but we need to modify convert script later * fix model_maps Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com> * fix convert_gptj Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com> * refine readme * refine --------- Signed-off-by: hshen14 <haihao.shen@intel.com> Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com> Co-authored-by: hshen14 <haihao.shen@intel.com> Co-authored-by: zhenwei-intel <zhenwei.liu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 87bd0d5 - Browse repository at this point
Copy the full SHA 87bd0d5View commit details -
Update NeuralChat inference with Docker (#197)
* Update README.md * Update README.md * Update README.md --------- Co-authored-by: Haihao Shen <haihao.shen@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3801c39 - Browse repository at this point
Copy the full SHA 3801c39View commit details -
Refined NeuralChat finetuning config (#222)
* refined finetuning config. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * updated readme for new finetuning config. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * simplified code. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> --------- Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 477752b - Browse repository at this point
Copy the full SHA 477752bView commit details -
Signed-off-by: Dong, Bo1 <bo1.dong@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 75dbdca - Browse repository at this point
Copy the full SHA 75dbdcaView commit details -
* support bloom Signed-off-by: Dong, Bo1 <bo1.dong@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 96b6749 - Browse repository at this point
Copy the full SHA 96b6749View commit details -
Configuration menu - View commit details
-
Copy full SHA for c3cf983 - Browse repository at this point
Copy the full SHA c3cf983View commit details -
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for be74cf9 - Browse repository at this point
Copy the full SHA be74cf9View commit details -
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9a1c7e3 - Browse repository at this point
Copy the full SHA 9a1c7e3View commit details -
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for dbbb6e8 - Browse repository at this point
Copy the full SHA dbbb6e8View commit details
Commits on Sep 4, 2023
-
Configuration menu - View commit details
-
Copy full SHA for cba649e - Browse repository at this point
Copy the full SHA cba649eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 97d2147 - Browse repository at this point
Copy the full SHA 97d2147View commit details -
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 7b07281 - Browse repository at this point
Copy the full SHA 7b07281View commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b8ce200 - Browse repository at this point
Copy the full SHA b8ce200View commit details -
Configuration menu - View commit details
-
Copy full SHA for 66edcff - Browse repository at this point
Copy the full SHA 66edcffView commit details
Commits on Sep 5, 2023
-
Configuration menu - View commit details
-
Copy full SHA for fdcba8b - Browse repository at this point
Copy the full SHA fdcba8bView commit details -
Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 53e8356 - Browse repository at this point
Copy the full SHA 53e8356View commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut
Configuration menu - View commit details
-
Copy full SHA for 6da5970 - Browse repository at this point
Copy the full SHA 6da5970View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4cdc5a1 - Browse repository at this point
Copy the full SHA 4cdc5a1View commit details -
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 2c5ff4a - Browse repository at this point
Copy the full SHA 2c5ff4aView commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f91ae7e - Browse repository at this point
Copy the full SHA f91ae7eView commit details -
fix finetuning and retrieval ut issue
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 4eebddb - Browse repository at this point
Copy the full SHA 4eebddbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 662be3f - Browse repository at this point
Copy the full SHA 662be3fView commit details
Commits on Sep 6, 2023
-
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9e6197b - Browse repository at this point
Copy the full SHA 9e6197bView commit details -
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 1d149de - Browse repository at this point
Copy the full SHA 1d149deView commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 176d6db - Browse repository at this point
Copy the full SHA 176d6dbView commit details -
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 02008e3 - Browse repository at this point
Copy the full SHA 02008e3View commit details -
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 1a8950f - Browse repository at this point
Copy the full SHA 1a8950fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 47e3c0e - Browse repository at this point
Copy the full SHA 47e3c0eView commit details -
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 45daa68 - Browse repository at this point
Copy the full SHA 45daa68View commit details -
avoid build from source in pylint
Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for cbf1d82 - Browse repository at this point
Copy the full SHA cbf1d82View commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut
Configuration menu - View commit details
-
Copy full SHA for 3c1c396 - Browse repository at this point
Copy the full SHA 3c1c396View commit details -
Configuration menu - View commit details
-
Copy full SHA for 839835c - Browse repository at this point
Copy the full SHA 839835cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 02a3fd4 - Browse repository at this point
Copy the full SHA 02a3fd4View commit details -
Configuration menu - View commit details
-
Copy full SHA for d09e2d2 - Browse repository at this point
Copy the full SHA d09e2d2View commit details -
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 2fce3f7 - Browse repository at this point
Copy the full SHA 2fce3f7View commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 93302d3 - Browse repository at this point
Copy the full SHA 93302d3View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4753ba5 - Browse repository at this point
Copy the full SHA 4753ba5View commit details -
Configuration menu - View commit details
-
Copy full SHA for 88d3b88 - Browse repository at this point
Copy the full SHA 88d3b88View commit details -
Configuration menu - View commit details
-
Copy full SHA for acee790 - Browse repository at this point
Copy the full SHA acee790View commit details -
Merge branch 'lvl/neuralchat_ut' of https://github.com/intel/intel-ex…
…tension-for-transformers into lvl/neuralchat_ut
Configuration menu - View commit details
-
Copy full SHA for 788e9d0 - Browse repository at this point
Copy the full SHA 788e9d0View commit details -
Configuration menu - View commit details
-
Copy full SHA for 77002b7 - Browse repository at this point
Copy the full SHA 77002b7View commit details -
Merge branch 'main' of https://github.com/intel/intel-extension-for-t…
…ransformers into lvl/neuralchat_ut Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 0bc4770 - Browse repository at this point
Copy the full SHA 0bc4770View commit details -
Configuration menu - View commit details
-
Copy full SHA for 36cf07f - Browse repository at this point
Copy the full SHA 36cf07fView commit details -
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for ff65c0b - Browse repository at this point
Copy the full SHA ff65c0bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 8e9553e - Browse repository at this point
Copy the full SHA 8e9553eView commit details -
Configuration menu - View commit details
-
Copy full SHA for ddfa9cb - Browse repository at this point
Copy the full SHA ddfa9cbView commit details -
fix retrieval sample.xlsx format issue
Signed-off-by: Lv, Liang1 <liang1.lv@intel.com>
Configuration menu - View commit details
-
Copy full SHA for de6e1e4 - Browse repository at this point
Copy the full SHA de6e1e4View commit details -
Configuration menu - View commit details
-
Copy full SHA for ed12613 - Browse repository at this point
Copy the full SHA ed12613View commit details