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
hf_text-generation-inference/integration-tests/models
History
Daniël de Kok 2358c2bb54
Add basic FP8 KV cache support (#2603) 
* Add basic FP8 KV cache support

This change adds rudimentary FP8 KV cache support. The support is
enabled by passing `--kv-cache-dtype fp8_e5m2` to the launcher. Doing so
uses this type for the KV cache. However support is still limited:

* Only the `fp8_e5m2` type is supported.
* The KV cache layout is the same as `float16`/`bfloat16` (HND).
* The FP8 KV cache is only supported for FlashInfer.
* Loading of scales is not yet supported.

* Fix Cargo.toml
 		2024-10-04 17:51:48 +02:00
..
__snapshots__ Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
test_bloom_560m.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_bloom_560m_sharded.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_chat_llama.py Lots of improvements (Still 2 allocators) (#2449) 2024-08-29 16:29:01 +02:00
test_completion_prompts.py Stream options. (#2533) 2024-09-19 20:50:37 +02:00
test_flash_awq.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_awq_sharded.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_deepseek_v2.py Add support for Deepseek V2 (#2224) 2024-07-19 17:23:20 +02:00
test_flash_falcon.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_gemma.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_gemma2.py Softcapping for gemma2. (#2273) 2024-07-22 18:27:10 +02:00
test_flash_gemma_gptq.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_gpt2.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_grammar_llama.py fix: correctly index into mask when applying grammar (#1618) 2024-03-01 18:22:01 +01:00
test_flash_llama.py feat(server): only compute prefill logprobs when asked (#406) 2023-06-02 17:12:30 +02:00
test_flash_llama_exl2.py Fixing exl2 and other quanize tests again. (#2419) 2024-08-15 11:12:51 +02:00
test_flash_llama_fp8.py Further fixes. (#2426) 2024-08-16 13:21:44 +02:00
test_flash_llama_fp8_kv_cache.py Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
test_flash_llama_gptq.py GPTQ CI improvements (#2151) 2024-07-05 14:12:16 +02:00
test_flash_llama_marlin.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_llama_marlin_24.py Improve the handling of quantized weights (#2250) 2024-07-19 09:37:39 +02:00
test_flash_llama_prefix.py Fix truffle (#2514) 2024-09-11 22:45:19 +02:00
test_flash_llama_prefix_flashdecoding.py Adding a test for FD. (#2516) 2024-09-16 17:00:54 +02:00
test_flash_medusa.py Revamp medusa implementation so that every model can benefit. (#1588) 2024-02-26 19:49:28 +01:00
test_flash_mistral.py fix(router): fix openapi and add jsonschema validation (#1578) 2024-02-21 11:05:32 +01:00
test_flash_mixtral.py Add tests for Mixtral (#2520) 2024-09-16 12:39:18 +02:00
test_flash_mixtral_gptq.py Add support for GPTQ-quantized MoE models using MoE Marlin (#2557) 2024-09-30 11:14:32 +02:00
test_flash_neox.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_neox_sharded.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_pali_gemma.py feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
test_flash_phi.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_phi35_moe.py feat: support phi3.5 moe (#2479) 2024-09-30 11:15:09 +02:00
test_flash_qwen2.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_santacoder.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_starcoder.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_starcoder2.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_flash_starcoder_gptq.py Upgrading the tests to match the current workings. (#2423) 2024-08-15 13:28:42 +02:00
test_grammar_llama.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_grammar_response_format_llama.py Upgrade fbgemm (#2398) 2024-08-12 14:08:38 +02:00
test_idefics.py feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
test_idefics2.py Refactor dead code - Removing all `flash_xxx.py` files. (#2166) 2024-07-05 10:29:56 +02:00
test_llava_next.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_lora_mistral.py feat: simple mistral lora integration tests (#2180) 2024-07-15 09:16:15 -04:00
test_mamba.py All integration tests back everywhere (too many failed CI). (#2428) 2024-08-16 21:19:46 +02:00
test_mllama.py Mllama flash version (#2585) 2024-10-02 11:22:13 +02:00
test_mpt.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_mt0_base.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_neox.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_neox_sharded.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_opt.py Fix the prefix for OPT model in opt_modelling.py #2370 (CI RUN) (#2371) 2024-08-07 23:14:02 -04:00
test_t5_sharded.py Add pytest release marker (#2114) 2024-06-25 16:53:20 +02:00
test_tools_llama.py Revert "Unroll notify error into generate response" (#2605) 2024-10-03 17:56:40 -04:00